Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Theory-of-Mind Reasoning on Andersen tales
Loading...
85.8
Belief Inference Accuracy
8B ↬ 405B
82.472
83.336
84.2
85.064
Jun 2, 2025
Belief Inference Accuracy
Goal Inference Accuracy
Overall Accuracy
Updated 22d ago
Evaluation Results
Method
Method
Links
Belief Inference Accuracy
Goal Inference Accuracy
Overall Accuracy
8B ↬ 405B
Solution Type=Ours, Ba...
2025.06
85.8
76
80.2
4B-depth ↬ 70B
Solution Type=Ours, Ba...
2025.06
85
71.3
77.1
70B-post-trained
Solution Type=Raw, Bac...
2025.06
84.6
66.3
74.1
4B-wide ↬ 70B
Solution Type=Ours, Ba...
2025.06
84
75.3
79
70B-zero-shot
Solution Type=Raw, Bac...
2025.06
83.6
60.6
70.2
8B ↬ 70B
Solution Type=Ours, Ba...
2025.06
82.6
76
78.8
Feedback
Search any
task
Search any
task