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

Hallucination Detection on MedicalQA

78.95AUROC

Combined: PC + SE

52.9559.766.4573.2Mar 22, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.03
78.9594.42
2026.03
77.2490.12
2026.03
77.0593.42
2026.03
75.5592.13
2026.03
74.9691.53
2026.03
70.1590.53
2026.03
69.0585.34
2026.03
68.8586.63
2026.03
68.1487.63
2026.03
68.0488.23
2026.03
67.1488.43
2026.03
66.7586.14
2026.03
66.6587.53
2026.03
65.4587.03
2026.03
64.9587.73
2026.03
64.8585.03
2026.03
64.3585.24
2026.03
64.2586.83
2026.03
63.5388.02
2026.03
63.4687.34
2026.03
62.8485.93
2026.03
62.6586.43
2026.03
61.3481.54
2026.03
56.9582.13
2026.03
56.5581.83
2026.03
56.0581.43
2026.03
55.1579.34
2026.03
53.9580.44