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

Natural Language Understanding on HellaSwag

85.6Accuracy

NLS

33.693647.169360.64574.1207Nov 21, 2024Feb 19, 2025May 21, 2025Aug 20, 2025Nov 18, 2025Feb 17, 2026May 19, 2026
Updated 12d ago

Evaluation Results

MethodLinks
2026.05
85.6
2026.05
76.44
2026.05
74.06
2026.05
59.7
2026.05
59.7
2026.05
59.6
2026.05
59.5
2026.05
59.2
2026.05
58.5
2026.05
58.4
2026.05
58
2026.05
57.9
2026.05
57.7
2026.05
57.3
2026.05
55.1
2026.05
54.5
2026.05
49.17
2026.05
47.3
2026.05
43.03
2024.11
40.89
2024.11
40.36
2024.11
40.18
2024.11
38.92
2026.05
38.68
2024.11
38.66
2024.11
38.46
2024.11
38.41
2024.11
38.33
2024.11
38.23
2024.11
38.19
2024.11
38.13
2024.11
38.08
2024.11
37.3
2024.11
37.19
2024.11
35.69