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

Language Modeling on LAMBADA standard (LS) (Accuracy)

73.67Accuracy (LAMBADA)

TWLA

-2.946816.944136.83556.7259Apr 8, 2026Apr 18, 2026Apr 29, 2026May 10, 2026May 20, 2026May 31, 2026Jun 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
73.67
2026.06
66.82
2026.04
65.57
2026.06
63.95
2026.04
63.26
2026.04
61.36
2026.06
60.94
2026.06
59.21
2026.06
57.33
2026.06
55.13
2026.04
45.55
2026.04
41.7
2026.04
39.31
2026.04
29.85
2026.04
28.62
2026.04
27.75
2026.04
25.88
2026.04
25.88
2026.04
24.98
2026.04
21.77
2026.04
20.05
2026.04
19.31
2026.04
19.1
2026.04
14.56
2026.04
14.13
2026.04
10.15
2026.04
10.11
2026.04
8.2
2026.04
1.22
2026.04
0.55
2026.04
0.26
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0
2026.04
0