Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Object Hallucination Detection on MSCOCO Qwen3-VL 3 (test)
Loading...
86.89
AUC
Overthinking Score
75.1068
78.1659
81.225
84.2841
Mar 8, 2026
AUC
AP
F1 Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUC
AP
F1 Score
Overthinking Score
Classifier=MLP
2026.03
86.89
53.72
71.15
Overthinking Score
Classifier=GB
2026.03
86.65
61.69
74.43
MetaToken
Classifier=MLP
2026.03
86.29
47
68.03
MetaToken
Classifier=GB
2026.03
84.21
38.06
74.43
HalLoc
2026.03
83.85
59.5
74.75
MetaToken
Classifier=LR
2026.03
79.49
27.6
47.27
Overthinking Score
Classifier=LR
2026.03
77.85
37.31
55.9
SVAR
2026.03
75.56
35.69
50.2
Feedback
Search any
task
Search any
task