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

General Language Evaluation on 5 Datasets Zero-shot

72.87Average Accuracy

QuEPT

33.942844.048954.15564.2611Feb 13, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
72.87
2026.02
72.65
2026.02
71.56
2026.02
70.99
2026.02
70.5
2026.02
69.51
2026.02
69.35
2026.02
69.22
2026.02
69.09
2026.02
68.72
2026.02
68.39
2026.02
67.04
2026.02
66.23
2026.02
66.05
2026.02
65.71
2026.02
65.48
2026.02
65.05
2026.02
64.71
2026.02
64.42
2026.02
64.3
2026.02
62.84
2026.02
61.62
2026.02
61.4
2026.02
59.11
2026.02
58.56
2026.02
57.16
2026.02
54.55
2026.02
54.31
2026.02
53.13
2026.02
51.6
2026.02
49.13
2026.02
35.7
2026.02
35.44