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

Theory of Mind on HiToM

87.08Accuracy

UserHarness

-3.483220.028443.5467.0516Feb 11, 2026Feb 28, 2026Mar 17, 2026Apr 4, 2026Apr 21, 2026May 8, 2026May 26, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2026.05
87.08
2026.05
87
2026.05
86.83
2026.05
86.83
2026.05
86.83
2026.05
86.75
2026.05
86.58
2026.05
86.58
2026.05
86.42
2026.05
86.42
2026.05
86.42
2026.05
86.25
2026.05
78
2026.05
77
2026.05
77
2026.05
75.5
2026.05
75.08
2026.05
74.92
2026.02
74.7
2026.05
73.42
2026.05
72.5
2026.05
72.08
2026.05
71
2026.05
70
2026.02
69.4
2026.05
68.5
2026.02
68
2026.05
67.8
2026.05
67.5
2026.05
66.83
2026.05
65.92
2026.05
65.3
2026.05
65.3
2026.02
60.7
2026.05
60.58
2026.05
59
2026.05
58.92
2026.02
58.6
2026.05
58
2026.05
57.9
2026.05
57.08
2026.05
56
2026.05
56
2026.02
55.8
2026.02
54.9
2026.02
54.7
2026.05
53.42
2026.05
50.92
2026.02
48.1
2026.05
44.5
2026.05
41.08
2026.05
37
2026.05
36
2026.05
25.6
2026.05
24.75
2026.05
20.6
2026.05
14.5
2026.05
12.67
2026.05
9.75
2026.05
8.17
2026.05
6.5
2026.05
3.58
2026.05
1.5
2026.05
0