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

Multi-risk safety monitoring on BeaverTails

80.1Accuracy (%)

TELLME

14.16431.28248.465.518Feb 7, 2025
Updated 6d ago

Evaluation Results

MethodLinks
2025.02
80.1
2025.02
79.1
2025.02
79
2025.02
78.8
2025.02
77.8
2025.02
77.6
2025.02
77.4
2025.02
77.3
2025.02
77
2025.02
76.6
2025.02
76.2
2025.02
76.2
2025.02
76.1
2025.02
75.8
2025.02
75.8
2025.02
75.8
2025.02
75
2025.02
74.6
2025.02
73
2025.02
73
2025.02
71.8
2025.02
70.8
2025.02
69.3
2025.02
69.3
2025.02
61.5
2025.02
59.8
2025.02
59.7
2025.02
59.2
2025.02
59.1
2025.02
59
2025.02
59
2025.02
58.8
2025.02
57.7
2025.02
57.6
2025.02
57.4
2025.02
57.1
2025.02
57
2025.02
56.8
2025.02
56.4
2025.02
56.3
2025.02
56.1
2025.02
56.1
2025.02
55.6
2025.02
54.4
2025.02
54.3
2025.02
54.2
2025.02
54.2
2025.02
54.1
2025.02
53.8
2025.02
53.5
2025.02
53.2
2025.02
52.4
2025.02
52.4
2025.02
52.3
2025.02
52.3
2025.02
51.5
2025.02
36.7
2025.02
23
2025.02
22.8
2025.02
20.2
2025.02
19.1
2025.02
16.9
2025.02
16.7