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

Zero-shot Evaluation on Evaluation Tasks Zero-shot Aggregate

79.95Avg. Accuracy

Baseline

28.761242.050655.3468.6294Feb 5, 2026Feb 22, 2026Mar 11, 2026Mar 28, 2026Apr 14, 2026May 1, 2026May 19, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
79.95
2026.05
76.28
2026.02
75.41
2026.05
74.82
2026.02
74.15
2026.05
73.93
2026.05
73.81
2026.05
73.63
2026.03
73.24
2026.05
73.18
2026.03
71.9
2026.03
71.86
2026.03
71.76
2026.03
71.67
2026.03
71.67
2026.02
71.11
2026.02
71.06
2026.02
71
2026.02
70.9
2026.02
70.86
2026.02
70.76
2026.02
70.71
2026.02
70.56
2026.05
70.51
2026.05
70.43
2026.02
70.05
2026.05
69.87
2026.02
69.78
2026.02
69.33
2026.05
69.32
2026.02
69.26
2026.02
69.01
2026.02
69
2026.02
68.94
2026.02
68.74
2026.02
68.73
2026.02
68.49
2026.02
68.47
2026.05
68.34
2026.02
67.84
2026.05
67.76
2026.05
67.75
2026.02
67.6
2026.02
67.6
2026.02
67.34
2026.02
67.26
2026.05
67.19
2026.02
67.18
2026.02
67.02
2026.02
67.01
2026.05
66.96
2026.02
66.82
2026.02
66.34
2026.02
66.22
2026.05
65.92
2026.02
65.77
2026.05
64.73
2026.05
64.06
2026.05
62.87
2026.05
62.13
2026.05
61.23
2026.05
60.21
2026.05
57.62
2026.05
55.35
2026.05
54.4
2026.05
39.91
2026.05
38.4
2026.05
35.54
2026.05
35.22
2026.05
34.82
2026.05
33.6
2026.05
32.03
2026.05
30.92
2026.05
30.73