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

Theory of Mind on BigToM

98.67Accuracy

UserHarness

15.293236.939158.58580.2309May 19, 2026May 20, 2026May 21, 2026May 22, 2026May 23, 2026May 24, 2026May 26, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2026.05
98.67
2026.05
98.25
2026.05
98.25
2026.05
98.17
2026.05
97.67
2026.05
97.25
2026.05
97.08
2026.05
96.67
2026.05
96.5
2026.05
96.17
2026.05
95.42
2026.05
95.25
2026.05
94.17
2026.05
93.83
2026.05
93.83
2026.05
93.5
2026.05
92.17
2026.05
92
2026.05
91.83
2026.05
90.5
2026.05
90.17
2026.05
89.8
2026.05
89.67
2026.05
88.5
2026.05
87.83
2026.05
87.33
2026.05
86.92
2026.05
86.92
2026.05
86.75
2026.05
86.25
2026.05
86
2026.05
85.5
2026.05
82.83
2026.05
81
2026.05
77.92
2026.05
77.5
2026.05
77.08
2026.05
76.42
2026.05
76.42
2026.05
74.42
2026.05
74
2026.05
73.5
2026.05
72.33
2026.05
61.67
2026.05
50.33
2026.05
47.5
2026.05
29.5
2026.05
18.5