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

Self-evaluation on VisualCoT

80.2AUROC

VAUQ

42.86452.55762.2571.943Feb 24, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.02
80.2
2026.02
77.8
2026.02
77.7
2026.02
77.2
2026.02
75.7
2026.02
75.5
2026.02
75.1
2026.02
74.7
2026.02
74.5
2026.02
68
2026.02
66.3
2026.02
65.8
2026.02
65.2
2026.02
65
2026.02
63.7
2026.02
62.3
2026.02
62.3
2026.02
61.4
2026.02
58.3
2026.02
56.7
2026.02
56.2
2026.02
56
2026.02
55.7
2026.02
55.1
2026.02
54.7
2026.02
54.7
2026.02
54.4
2026.02
53.3
2026.02
52.5
2026.02
51.1
2026.02
49.9
2026.02
46.7
2026.02
46.5
2026.02
44.5
2026.02
44.5
2026.02
44.3