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

General Language Understanding on GLUE

92.5Accuracy

Full FT

29.621645.945862.2778.5942Dec 19, 2025Dec 23, 2025Dec 28, 2025Jan 2, 2026Jan 6, 2026Jan 11, 2026Jan 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
92.5
2025.12
92.3
2025.12
91.9
2025.12
91.7
2025.12
91.3
2025.12
90.9
2025.12
90.7
2025.12
90.2
2025.12
89.6
2025.12
89.4
2025.12
89.1
2025.12
88.9
2025.12
88.5
2025.12
88.4
2025.12
87.9
2025.12
87.8
2025.12
87.5
2025.12
86.7
2025.12
85.8
2026.01
85.74
2026.01
85.49
2025.12
85.1
2025.12
84.4
2026.01
84.33
2026.01
84.33
2025.12
84.3
2026.01
84.27
2026.01
84.23
2025.12
84
2026.01
83.63
2026.01
83.63
2026.01
83.63
2025.12
83.5
83.43
2026.01
82.87
2026.01
82.82
82.62
2026.01
81.66
2026.01
81.26
2026.01
81.11
2026.01
80.81
2026.01
80.65
2026.01
80.3
2026.01
80.3
2026.01
78.44
2026.01
76.98
2026.01
76.62
2026.01
76.52
2026.01
76.37
75.26
2026.01
73.95
71.49
2026.01
69.22
2026.01
67.76
2026.01
62.47
2026.01
58.79
2026.01
58.29
2026.01
55.87
2026.01
49.87
2026.01
47.61
34.96
2026.01
33.65
2026.01
33.65
2026.01
32.54
2026.01
32.54
2026.01
32.04