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

Reasoning on WinoGrande

85.2Accuracy

InternLM2-20B

51.81660.48369.1577.817Mar 26, 2024Jul 28, 2024Nov 29, 2024Apr 2, 2025Aug 4, 2025Dec 6, 2025Apr 10, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2024.03
85.2
2024.03
84.7
2024.03
77.3
2024.03
76.2
2024.03
75.3
2024.03
75
2024.03
74.8
2024.03
74.6
2025.03
74
2026.04
74
2025.03
72.9
2025.03
72.8
2025.03
72.8
2025.03
72.6
2025.03
72.6
2025.03
72.5
2024.03
72.3
2025.03
72.1
2025.03
71.1
2025.03
71
2025.03
71
2024.03
70
2026.02
70
2026.02
70
2026.04
69.53
2024.03
69.5
2026.04
68.9
2026.04
68.82
2024.03
68.7
2024.03
68.7
2024.03
68.6
2026.04
68.5
2026.02
68
2026.04
67.64
2024.03
67.5
2026.04
67.2
2025.03
67.1
2026.04
66.7
2026.04
66.7
2026.04
66.3
2026.04
66.3
2026.04
66.2
2026.02
66
2025.05
65.98
2025.05
65.98
2026.04
65.9
2024.03
65.8
2024.03
65.8
2026.04
65.8
2026.04
65.48
2026.02
65
2026.04
64.96
2025.05
64.72
2025.03
64.7
2025.05
64.64
2025.05
64.4
2026.04
64.3
2026.04
64.1
2025.05
63.3
2025.03
62.4
2024.03
61.7
2024.03
60.9
2025.03
60.9
2025.06
60.1
2026.04
60
2026.04
59.9
2025.06
59.4
2025.06
59.2
2025.06
59.2
2026.04
59
2026.04
58.64
2026.04
58.54
2025.03
58.4
2026.04
58.3
2026.04
58.3
2025.06
58.1
2025.06
57.9
2026.04
57.8
2026.04
57.62
2025.05
56.83
2025.06
56.6
2025.03
56.6
2026.04
56.2
2025.06
55.8
2024.03
55.7
2025.06
55.4
2026.04
55.25
2025.06
55.2
2026.04
55.09
2026.04
54.96
2025.03
54.7
2025.06
54.6
2025.05
54.46
2024.03
54.2
2026.04
54.06
2026.04
53.41
2025.06
53.4
2025.06
53.3
2025.03
53.1
2025.03
53.1
Showing 100 of 135 rows