Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Hallucination Detection on TextVQA (val)
Loading...
96.98
AUPRC
Lyapunov Probes
85.4464
88.4407
91.435
94.4293
Mar 6, 2026
AUPRC
Updated 2mo ago
Evaluation Results
Method
Method
Links
AUPRC
Lyapunov Probes
Model=Qwen-2.5-VL
2026.03
96.98
Probe
Model=Qwen-2.5-VL
2026.03
95.61
Lyapunov Probes
Model=LLaVA-1.5
2026.03
89.02
Probe
Model=LLaVA-1.5
2026.03
85.89
Feedback
Search any
task
Search any
task