Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Factual A/B test on I-HallA History 99 pairs (test)
Loading...
83
Pairwise Accuracy
FAGER
51.8
59.9
68
76.1
May 18, 2026
Pairwise Accuracy
Updated 2mo ago
Evaluation Results
Method
Method
Links
Pairwise Accuracy
FAGER
2026.05
83
FineGRAIN
2026.05
72
VQAScore
2026.05
53
Feedback
Search any
task
Search any
task
