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

Hallucination Detection on VQA-Med 2019 (All)

76.1AUC

VASE + V-Loop

36.569646.832357.09567.3577Jan 26, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.01
76.161.76
2026.01
75.9260.79
2026.01
74.1457.67
2026.01
72.0754.18
2026.01
70.5555.82
2026.01
70.2555.28
2026.01
70.2555.28
2026.01
69.5654.9
2026.01
68.868.43
2026.01
68.1944.71
2026.01
67.2365.22
2026.01
67.0957.33
2026.01
67.0253.91
2026.01
66.3546.71
2026.01
66.3546.71
2026.01
66.0753.77
2026.01
66.0165.62
2026.01
65.6665.03
2026.01
63.2852.15
2026.01
62.9550.14
2026.01
62.9550.14
2026.01
62.5854.87
2026.01
60.9148.78
2026.01
60.9148.78
2026.01
60.1747.9
2026.01
56.4234.84
2026.01
55.9142.77
2026.01
55.9142.77
2026.01
55.4235.4
2026.01
54.441.3
2026.01
54.3641.31
2026.01
51.938.72
2026.01
51.938.72
2026.01
45.6448.61
2026.01
45.647.82
2026.01
44.4138.33
2026.01
43.6435.69
2026.01
39.7437.45
2026.01
38.0932.09