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

Uncertainty Estimation on JudgeBench (test)

71.53AUROC

Energy

40.933248.876656.8264.7634Dec 23, 2025
Updated 3d ago

Evaluation Results

MethodLinks
2025.12
71.53
2025.12
71.17
2025.12
69.2
2025.12
69.12
2025.12
69.05
2025.12
68.86
2025.12
68.46
2025.12
67.79
2025.12
66.87
2025.12
65.63
2025.12
64.47
2025.12
64.42
2025.12
64.33
2025.12
64.27
2025.12
63.88
2025.12
63.74
2025.12
63.72
2025.12
63.17
2025.12
62.9
2025.12
62.04
2025.12
62.03
2025.12
60.63
2025.12
60.36
2025.12
60.26
2025.12
59.98
2025.12
59.62
2025.12
59.61
2025.12
59.6
2025.12
59.6
2025.12
59.13
2025.12
58.14
2025.12
58.13
2025.12
57.95
2025.12
55.36
2025.12
54.71
2025.12
54.19
2025.12
53.5
2025.12
53.34
2025.12
52.38
2025.12
52.24
2025.12
52.06
2025.12
51.55
2025.12
51.53
2025.12
51.48
2025.12
51.47
2025.12
51.31
2025.12
51.2
2025.12
51.11
2025.12
51.08
2025.12
50.87
2025.12
50.85
2025.12
50.81
2025.12
50.79
2025.12
50.72
2025.12
50.67
2025.12
50.56
2025.12
50.07
2025.12
50
2025.12
49.99
2025.12
49.98
2025.12
49.82
2025.12
49.34
2025.12
48.8
2025.12
47.99
2025.12
47.81
2025.12
46.83
2025.12
46.82
2025.12
46.81
2025.12
46.77
2025.12
46.69
2025.12
46.54
2025.12
46.44
2025.12
46.25
2025.12
45.99
2025.12
43.54
2025.12
43.15
2025.12
42.11