Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Theory of Mind reasoning on MMToM
Loading...
83.3
Accuracy
Thinking-RFT
37.644
49.497
61.35
73.203
Jun 8, 2026
Accuracy
Avg Delta vs SFT
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Avg Delta vs SFT
Thinking-RFT
Modality=Lan.+Vis.
2026.06
83.3
82.2
Thinking-RFT
Modality=Lan.
2026.06
78.5
-
SFT
Modality=Lan.+Vis.
2026.06
74.3
74.75
SFT
Modality=Lan.
2026.06
73.02
-
AutoToM
Modality=Lan.+Vis.
2026.06
56.9
58
SimToM
Modality=Lan.+Vis.
2026.06
50.6
50.1
Zero-shot
Modality=Lan.+Vis.
2026.06
45
44.15
Zero-shot
Modality=Lan.
2026.06
39.4
-
Feedback
Search any
task
Search any
task