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

Common Sense Reasoning on ARC Challenge

89.6Accuracy

DASD

19.60837.77955.9574.121Nov 6, 2025Dec 13, 2025Jan 19, 2026Feb 25, 2026Apr 3, 2026May 10, 2026Jun 17, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.05
89.674.3
2026.05
88.971.6
2026.05
88.869.7
2026.05
88.471.1
2026.05
8870.8
2026.05
7856.7
2026.05
7756.3
2026.05
76.254.7
2026.05
75.547
2026.05
74.945.4
2026.05
74.545.9
2026.05
74.453.1
2026.05
7452.3
2026.05
73.344.8
2026.05
7043
2025.11
56.7-
2025.11
55.3-
2025.11
53.8-
2025.11
52.7-
2025.11
52.7-
2025.11
52-
2025.11
51.6-
2025.11
51-
2025.11
51-
2025.11
50.3-
2025.11
49-
2025.11
48.3-
2025.11
48.2-
2025.11
48.1-
2025.11
47-
2025.11
45-
2025.11
44.6-
2025.11
44-
2025.11
44-
2025.11
43-
2025.11
42.1-
2025.11
41.1-
2025.11
41-
2025.11
41-
2025.11
40.9-
2025.11
40.7-
2025.11
40.1-
2025.11
40-
2025.11
40-
2025.11
38.7-
2025.11
37.4-
2025.11
36.7-
2025.11
36-
2025.11
35.7-
2025.11
34.8-
2025.11
34.3-
2025.11
33.6-
2025.11
32-
2025.11
27.8-
2026.06
27.57-
2026.06
27.23-
2026.06
26.55-
2026.06
26.39-
2026.06
26.32-
2026.06
25.78-
2026.06
25.61-
2025.11
23.9-
2025.11
22.3-