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

Spatial Reasoning on MindCube (tiny)

94.5Accuracy

Human

17.976837.843457.7177.5766Nov 10, 2025Dec 13, 2025Jan 16, 2026Feb 19, 2026Mar 25, 2026Apr 28, 2026Jun 1, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.05
94.5
2026.05
88.6
2026.06
85
2026.05
83
2026.06
81.8
2026.06
81
2026.06
80.5
2026.06
79.2
2026.05
75.8
2026.06
75.2
2026.05
73.8
2026.05
70.9
2026.05
70.86
2026.06
70.7
2026.05
68.4
2026.05
63.46
2026.05
62.01
2026.05
60.4
2026.05
57.6
2026.05
57.59
2026.06
55.5
2026.05
48.84
2026.05
48.8
2026.06
48.42
2026.06
48
2025.11
45.4
2025.11
45.1
2025.11
44.8
2026.06
44.75
2026.06
44.21
2025.11
44
2026.05
43.5
2026.05
43.17
2025.11
42.5
2025.11
42.2
2026.05
40.86
2026.05
40.6
2025.11
40.5
2026.05
40.2
2026.06
40.17
2026.05
39.7
2025.12
39.6
2025.11
39
2026.06
38.81
2025.11
38.8
2026.06
38.76
2026.06
38.39
2026.06
38.3
2026.06
38.02
2026.05
38
2026.05
37.9
2026.06
37.37
2025.11
36.7
2025.11
36.4
2026.06
36.36
2026.05
36
2025.11
36
2025.11
36
2025.11
36
2025.11
35.9
2025.11
35.3
34.9
2025.11
34.9
2026.05
34.7
2025.11
34.6
2025.12
34.2
2026.06
33.71
2025.11
33.5
2026.06
33.28
2026.06
33.26
2026.06
33.21
2025.12
33.1
2026.06
33.02
2026.05
33
2026.06
32.66
2026.06
32.65
2026.06
32.35
2026.06
32.29
2026.06
32.06
2025.12
31.9
2026.06
29.5
2026.05
29.4
2026.06
29.26
2026.06
20.92