Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Factuality Detection on CSQA (test)
Loading...
74.8
AUROC
TraceDet
53.376
58.938
64.5
70.062
Mar 17, 2026
AUROC
Updated 2mo ago
Evaluation Results
Method
Method
Links
AUROC
TraceDet
Source Dataset=TriviaQ...
2026.03
74.8
DynHD
Source Dataset=TriviaQ...
2026.03
73.6
DynHD
Source Dataset=HotpotQ...
2026.03
71.4
TraceDet
Source Dataset=HotpotQ...
2026.03
66.2
TSV
Source Dataset=HotpotQ...
2026.03
63.2
CCS
Source Dataset=HotpotQ...
2026.03
56.6
TSV
Source Dataset=TriviaQ...
2026.03
56.2
CCS
Source Dataset=TriviaQ...
2026.03
54.2
Feedback
Search any
task
Search any
task