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

Question Answering on Winogrande (WG)

72.77Accuracy

LLaMA-3 8B

52.001257.393162.78568.1769Nov 21, 2024Feb 9, 2025May 1, 2025Jul 20, 2025Oct 9, 2025Dec 28, 2025Mar 19, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.02
72.77
2026.02
70.96
2026.02
70.17
2025.07
69.61
2025.07
69.46
2026.02
69.14
2025.07
68.82
2025.07
68.82
2025.07
67.72
2025.07
67.6
2026.02
67.4
2025.07
67.4
2025.07
67.32
2026.02
67.25
2025.07
67.1
2025.07
66.93
2026.02
66.9
2025.07
66.9
2026.02
66.8
2026.02
66.69
2025.07
66.5
2026.02
66.22
2025.07
65.82
2025.07
65.67
2025.07
65.67
2025.07
65.43
2026.02
65.19
2026.03
65.19
2026.02
65.11
2025.07
64.96
2025.07
64.9
2026.02
64.88
2025.07
64.7
2026.02
64.64
2026.02
63.93
2026.03
63.85
2026.02
63.75
2026.02
63.38
2026.03
63.22
2026.02
62.9
2026.02
62.38
2026.03
62.19
2024.11
61.96
2026.03
61.88
2024.11
61.8
2024.11
61.8
2024.11
61.72
2024.11
61.72
2024.11
61.72
2024.11
61.72
2024.11
61.56
2024.11
61.56
2024.11
61.56
2024.11
61.56
2026.02
61.56
2024.11
61.48
2024.11
61.48
2026.02
61.38
2026.02
61.33
2024.11
61.25
2026.02
61.25
2024.11
61.17
2026.02
61.09
2026.02
60.77
2026.02
60.77
2026.02
60.62
2026.02
60.3
2026.02
59.91
2026.02
59.35
2026.02
59.35
2024.11
57.3
2024.11
57.22
2024.11
57.22
2024.11
57.22
2024.11
57.22
2024.11
57.22
2024.11
57.14
2024.11
57.06
2024.11
57.06
2024.11
56.99
2024.11
56.99
2024.11
56.99
2024.11
56.91
2026.02
56.91
2024.11
56.75
2024.11
56.75
2026.02
56.67
2026.02
56.27
2026.01
55.64
2026.01
55.17
2026.01
54.06
2026.01
53.67
2026.01
53.59
2026.01
53.35
2026.01
53.2
2026.01
53.12
2026.01
53.04
2026.02
52.96
2025.12
52.9
2025.12
52.8
Showing 100 of 124 rows