Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Factuality Detection on HotpotQA (test)
Loading...
73.3
AUROC
DynHD
50.94
56.745
62.55
68.355
Mar 17, 2026
AUROC
Updated 2mo ago
Evaluation Results
Method
Method
Links
AUROC
DynHD
Source Dataset=TriviaQ...
2026.03
73.3
TSV
Source Dataset=TriviaQ...
2026.03
65.5
TraceDet
Source Dataset=CSQA, M...
2026.03
65
DynHD
Source Dataset=CSQA, M...
2026.03
64.9
TSV
Source Dataset=CSQA, M...
2026.03
59.1
TraceDet
Source Dataset=TriviaQ...
2026.03
57.4
CCS
Source Dataset=CSQA, M...
2026.03
54
CCS
Source Dataset=TriviaQ...
2026.03
51.8
Feedback
Search any
task
Search any
task