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

Question Answering on ARC Challenge (Accuracy)

87.3Accuracy (ARC)

Frozen LLM graph

24.941.157.373.5Jul 21, 2025Sep 3, 2025Oct 18, 2025Dec 1, 2025Jan 15, 2026Feb 28, 2026Apr 14, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.04
87.3
2026.04
78.2
2026.04
75.9
2026.04
75.3
2026.04
73.9
2026.04
67.1
2026.03
60.5
2026.03
60.5
2026.04
58.1
2026.04
57.9
2026.04
57.9
2026.04
57.5
2026.04
56.6
2025.10
56.57
2026.04
56.5
2026.04
56.5
2026.04
56.5
2026.04
56.4
2026.04
56.4
2026.04
56.4
2026.04
56.4
2026.04
56.4
2025.10
56.4
2026.04
56.2
2026.04
56.1
2026.04
55.97
2026.04
55.6
2026.04
55.6
2026.04
54.5
2026.04
53.8
2026.04
53.5
2026.04
53.4
2026.04
52.5
2026.04
52.2
2026.04
50.8
2026.04
49.23
2026.04
49.1
2026.04
48.7
2026.04
48.5
2026.04
48
2026.04
47.9
2026.04
47.2
2026.04
46.2
2026.04
46.16
2026.04
45.7
2026.04
45.5
2026.04
44.62
2026.04
44.37
2026.04
44.3
2026.04
44.11
2026.04
43.29
2026.04
43.17
2025.09
42.97
2026.04
42.83
2025.09
42.19
2025.09
41.41
2025.09
41.41
2025.07
40.8
2025.07
40.53
2026.04
39.9
2026.04
39.6
2025.07
39.23
2025.07
38.89
2025.07
38.74
2026.04
38.7
2026.04
38.6
2025.07
38.32
2026.04
38.3
2025.07
38.1
2026.04
38.1
2025.07
37.17
2025.07
36.92
2025.07
36.69
2025.07
36.45
2025.07
36.26
2025.07
36.26
2026.04
35.6
2026.04
35.53
2026.04
34.8
2025.07
34.73
2026.04
34.64
2026.04
34.5
2026.04
33.36
2025.07
32.11
2025.09
32.03
2026.04
31.9
2026.03
31.5
2026.04
31.22
2026.03
31
2026.04
29.7
2025.09
29.69
2026.03
29
2026.04
28.7
2025.07
28.58
2025.07
28.33
2025.09
28.12
2026.04
27.9
2026.04
27.32
2026.04
27.32
2026.04
27.3
Showing 100 of 142 rows