Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination Detection on VizWiz (val)
Loading...
85.17
AUPRC
Lyapunov Probes
76.694
78.8945
81.095
83.2955
Mar 6, 2026
AUPRC
Updated 2mo ago
Evaluation Results
Method
Method
Links
AUPRC
Lyapunov Probes
Model=Qwen-2.5-VL
2026.03
85.17
Probe
Model=Qwen-2.5-VL
2026.03
84.04
Lyapunov Probes
Model=LLaVA-1.5
2026.03
83.18
Probe
Model=LLaVA-1.5
2026.03
77.02
Feedback
Search any
task
Search any
task