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

Hallucination Detection on HaluEval (test)

97.1AUC-ROC

CDES

54.688865.699476.7187.7206May 30, 2025Jul 9, 2025Aug 18, 2025Sep 27, 2025Nov 6, 2025Dec 16, 2025Jan 26, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2025.05
97.1--
2025.05
97.1--
2025.05
96.9--
2025.05
96--
2025.05
95.4--
2025.05
95.4--
2025.05
95.4--
2025.05
95.3--
2025.05
94.5--
2025.05
94.1--
2025.05
93.9--
2025.05
93.8--
2025.05
93.7--
2025.05
93.7--
2025.05
93.5--
2025.05
93.4--
2025.05
93.1--
2025.05
93.1--
2025.05
92.9--
2025.05
92.8--
2025.05
92.6--
2025.05
92.4--
2025.05
92.1--
2025.05
92.1--
2025.05
91.4--
2025.05
91.2--
2025.05
91--
2025.05
90.5--
2025.05
90.5--
2025.05
90.1--
2025.05
89.5--
2025.05
89.5--
2025.05
89.4--
2025.05
88.3--
2025.05
87--
2025.05
86.1--
2026.01
80.7979.5468.51
2026.01
78.1574.1561.14
2025.05
78.1--
2025.05
76.9--
2025.05
76--
2025.05
76--
2025.05
75.8--
2026.01
75.7272.8963.15
2025.05
75.2--
2026.01
74.6268.3364.4
2025.05
74.5--
2026.01
73.4371.1954.8
2025.05
73.3--
2025.05
72.6--
2026.01
72.0171.9760.64
2025.05
71.9--
2026.01
71.3367.6353.15
2025.05
71.3--
2025.05
70.5--
2026.01
67.9564.9352.21
2026.01
65.7763.0145.47
2026.01
65.4463.1348.23
2026.01
65.2463.5254.33
2026.01
65.1863.5348.09
2026.01
65.1563.7154.61
2026.01
64.8960.7246.39
2026.01
64.5460.8945.13
2025.05
64.4--
2026.01
64.3760.9250.86
2026.01
64.2961.8345.49
2026.01
63.9361.3351.87
2026.01
63.6161.1644.75
2025.05
63.1--
2026.01
62.8560.5943.85
2026.01
62.7461.6152.01
2026.01
62.6660.346.42
2025.05
62.5--
2025.05
62.3--
2026.01
62.2959.642.24
2026.01
62.1158.2443.06
2026.01
61.9860.3246.29
2026.01
61.7357.8542.15
2026.01
61.5757.9945.39
2026.01
61.3159.3646.01
2025.05
61.3--
2026.01
60.6559.1144.51
2026.01
60.5459.0450.37
2025.05
60.2--
2026.01
60.1658.8948.42
2026.01
60.1358.4448.01
2026.01
59.7859.1440.47
2026.01
59.4758.3346.91
2026.01
59.4457.7240.77
2025.05
59.4--
2026.01
59.3955.9446.35
2025.05
58.2--
2026.01
57.9856.0141.69
2025.05
57.9--
2025.05
57.6--
2026.01
57.4654.840.47
2026.01
57.1255.2643.06
2025.05
57.1--
2026.01
56.5955.3945.57
2026.01
56.3254.0443.75
Showing 100 of 126 rows