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

Commonsense Reasoning on HellaSwag (Score)

95.45HellaSwag Score

LD-MoLE

28.245245.692663.1480.5874Feb 16, 2025Apr 23, 2025Jun 28, 2025Sep 2, 2025Nov 7, 2025Jan 12, 2026Mar 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
95.45
2025.09
94.95
2025.09
94.06
2025.09
94.03
2025.09
93.6
2025.09
93.44
2026.02
90.11
2025.09
88.71
2025.09
88
2025.09
87.47
2025.09
87.31
2025.09
87.09
2025.09
83.35
2026.03
69
2026.03
68.6
2026.03
68.6
2026.03
67.8
2026.03
67.4
2026.03
67
2026.03
66.8
2026.03
66.4
2026.03
64.8
2025.11
61.62
2025.11
60.69
2026.03
60.4
2025.11
59.9
2025.11
59.52
2025.02
57.94
2025.11
57.82
2025.11
57.32
2025.11
57.14
2025.11
56.9
2025.02
56.06
2025.02
55.85
2025.02
55.47
2025.11
55.09
2025.11
54.93
2025.11
53.98
2025.11
53.69
2025.02
53.49
2025.11
53.42
2025.02
53.34
2025.02
53.08
2025.11
52.91
2025.11
52.84
2025.11
52.73
2025.11
51.31
2025.11
50.23
2025.02
47.29
2025.02
46.62
2025.02
45.43
2025.02
44.11
2026.01
38.11
2026.01
37.8
2026.01
30.83