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

Theory of Mind Reasoning on FanToM

96.131st-Order Accuracy

RECTOM

62.236471.035779.83588.6343Jun 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
96.1399.397.53
2026.06
92.8286.0189.81
2026.06
92.2792.3192.28
2026.06
91.1695.893.21
2026.06
91.1691.6191.36
2026.06
89.581.8286.11
2026.06
88.9586.7187.96
2026.06
87.2984.6286.11
2026.06
86.7485.3186.11
2026.06
82.3289.5185.49
2026.06
78.4585.3181.48
2026.06
77.3590.2183.02
2026.06
76.2479.7277.78
2026.06
74.5991.6182.1
2026.06
71.2780.4275.31
2026.06
63.5475.5268.83