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

Zero-shot Reasoning on ARC-Easy

97.43Zero-shot Accuracy

WeDLM-8B

-1.817223.948949.71575.4811Jul 25, 2023Jan 14, 2024Jul 6, 2024Dec 27, 2024Jun 19, 2025Dec 10, 2025Jun 2, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
97.43
2025.12
97.01
2025.12
96.17
2025.12
96.09
2025.12
94.32
2025.12
93.27
2025.12
93.27
2026.06
86.99
2026.06
84.3
2026.06
82.7
2026.06
81.9
2026.06
81.86
2026.06
81.52
2026.06
81.36
2026.06
81.12
2026.06
80.13
2026.06
80.09
2025.07
79.42
2026.06
79.42
2025.07
77.82
2025.07
77.62
2026.06
77.48
2026.06
77.4
2025.07
77.26
2026.06
76.6
2025.07
76.3
2026.06
76.3
2026.06
76.26
2026.04
76
2026.06
75.72
2026.06
74.83
2026.02
74.6
2025.07
74.58
2026.06
74.33
2025.07
74.03
2025.07
74.01
2025.07
73.95
2026.06
73.32
2025.07
73.06
2026.06
72.9
2026.02
72.6
2025.07
71.89
2026.06
71.84
2025.07
71.46
2026.06
71.17
2026.06
71.03
2025.07
70.97
2026.06
70.96
2026.06
70.66
2025.07
70.22
2025.07
69.61
2025.07
68.63
2025.07
65.99
2026.04
65
2026.04
64
2025.07
63.93
2025.07
63.26
2026.02
63.1
2026.04
63
2026.04
62
2025.07
60.48
2023.07
59.81
2023.07
59.81
2023.07
59.72
2023.07
59.72
2023.07
58.96
2023.07
54.38
2023.07
54.38
2025.07
54.06
2026.04
53
2025.07
52.99
2025.07
51.06
2026.04
51
2026.04
49
2025.07
48.63
2026.02
47.6
2026.04
45
2026.02
34.4
2026.02
33.8
2026.04
33
2026.04
30
2026.04
29
2026.02
28.3
2025.07
27.99
2025.07
27.99
2025.07
26.18
2023.07
25.34
2026.04
25
2026.04
11
2026.04
11
2026.04
5
2026.04
5
2026.04
4
2026.04
2