Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Metric Sensitivity Analysis on Quilt-1M Visual Hallucination
Loading...
0.9
Performance Score
BERTScore
0.0888
0.2994
0.51
0.7206
Mar 17, 2026
Performance Score
Performance Delta (%)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Performance Score
Performance Delta (%)
BERTScore
Focus=Semantic
2026.03
0.9
2.2
PathGLS (Sl)
Focus=Consistency
2026.03
0.82
9.9
PathGLS (Sg)
Focus=Visual-Text
2026.03
0.46
40.3
RadGraph
Focus=Entity
2026.03
0.19
38.7
BLEU-4
Focus=Lexical
2026.03
0.12
25
Feedback
Search any
task
Search any
task