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

Zero-shot Evaluation on 6 Downstream Tasks

80.05Average Accuracy

Dense

33.426845.530957.63569.7391Feb 6, 2026Feb 22, 2026Mar 11, 2026Mar 28, 2026Apr 14, 2026May 1, 2026May 18, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.02
80.05
2026.02
78.69
2026.02
75.81
2026.02
75.12
2026.02
74.89
2026.05
74.3
2026.05
73.3
2026.02
72.86
2026.02
72.72
2026.02
72.18
2026.02
71.85
2026.02
71.4
2026.05
71.34
2026.05
71.3
2026.05
71.19
2026.05
71.09
2026.05
70.62
2026.05
70.57
2026.05
70.5
2026.05
70.3
2026.05
70.19
2026.05
70.11
2026.05
69.3
2026.02
69.23
2026.05
67.83
2026.05
67.67
2026.05
67.67
2026.05
67.44
2026.05
67.25
2026.02
67.08
2026.02
67.05
2026.04
65.6
2026.04
64.9
2026.02
63.7
2026.02
63.03
2026.02
61.79
2026.04
60.6
2026.04
60.3
2026.02
59.71
2026.04
59.1
2026.04
59.1
2026.04
58.9
2026.04
58.5
2026.04
58.5
2026.04
57.3
2026.04
57.2
2026.05
56.59
2026.04
56.3
2026.05
56.09
2026.05
54.51
2026.05
54.23
2026.05
52.99
2026.05
52.52
2026.05
52.13
2026.05
52.03
2026.05
51.92
2026.05
51.85
2026.05
50.67
2026.05
50.09
2026.05
48.63
2026.05
48.52
2026.05
47.72
2026.05
45.1
2026.05
43.64
2026.02
39.31
2026.02
37.45
2026.05
37.32
2026.05
36.3
2026.05
36.11
2026.05
35.22