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

Zero-shot Reasoning on HellaSwag (200 items subset)

68Accuracy

HQMQ s192 r6 + Med3x

20.6832.96545.2557.535May 12, 2026May 14, 2026May 16, 2026May 19, 2026May 21, 2026May 23, 2026May 26, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2026.05
68
2026.05
65
2026.05
64
2026.05
63
2026.05
49.5
2026.05
48
2026.05
47.5
2026.05
47.5
2026.05
47.5
2026.05
46.5
2026.05
45.5
2026.05
44
2026.05
41.5
2026.05
37
2026.05
33.5
2026.05
30
2026.05
22.5