Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Object Hallucination Detection on MSCOCO Average performance across VLMs (test)
Loading...
87.33
AUC
Overthinking Score
77.8972
80.3461
82.795
85.2439
Mar 8, 2026
AUC
AP
F1
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUC
AP
F1
Overthinking Score
Classifier=MLP
2026.03
87.33
58.12
72.86
Overthinking Score
Classifier=GB
2026.03
87.3
61.54
75.97
MetaToken
Classifier=MLP
2026.03
83.83
45.45
67.32
MetaToken
Classifier=GB
2026.03
83.46
44.61
72.51
HalLoc
2026.03
81.17
54.36
71.85
Overthinking Score
Classifier=LR
2026.03
80.46
42.56
65.44
MetaToken
Classifier=LR
2026.03
79.6
36.32
56.14
SVAR
2026.03
78.26
39.71
55.8
Feedback
Search any
task
Search any
task