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

Commonsense Question Answering on WinoGrande

77.82Accuracy

Llama-3.1-8B-Instruct

46.963254.974162.98570.9959Oct 29, 2025Dec 3, 2025Jan 8, 2026Feb 13, 2026Mar 21, 2026Apr 26, 2026Jun 1, 2026
Updated 20h ago

Evaluation Results

MethodLinks
2026.06
77.82
2026.06
75.22
2026.06
74.9
2025.10
73
2025.10
72
2026.05
71.5
2026.05
71
2026.05
71
2026.06
70.72
2026.05
70.7
2026.05
70.5
2026.05
70.1
2025.10
70
2026.05
69.8
2026.05
69.6
2026.05
69.6
2026.05
69.4
2026.05
69.3
2026.05
69.1
2026.05
69.1
2025.10
69
2025.10
69
2026.05
69
2026.05
68.9
2026.05
68.5
2026.05
68.3
2025.10
68
2025.10
68
2025.10
68
2026.06
67.88
2026.05
67.8
2026.05
67.4
2026.05
67.4
2026.04
67.17
2025.10
67
2026.05
66.5
2026.05
66.2
2025.10
66
2025.10
66
2026.05
65.4
2026.06
65.35
2026.05
64.8
2025.10
64
2025.10
64
2026.05
62.8
2026.05
62.6
2025.10
62
2025.10
62
2025.10
62
2026.06
61.01
2025.10
61
2025.10
61
2025.10
60
2025.10
60
2025.10
59
2026.04
58.27
2026.04
58.01
2025.10
58
2026.06
57.85
2026.05
57.5
2026.05
57
2026.05
57
2026.06
56.75
2026.05
56.4
2026.05
56.3
2025.10
55
2026.06
54.93
2026.04
54.54
2025.10
54
2026.05
52.1
2026.05
51.5
2026.04
49.49
2026.04
48.15