Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Factuality Detection on TriviaQA (test)
Loading...
85.5
AUROC
DynHD
48.684
58.242
67.8
77.358
Mar 17, 2026
AUROC
Updated 2mo ago
Evaluation Results
Method
Method
Links
AUROC
DynHD
Source Dataset=HotpotQ...
2026.03
85.5
TraceDet
Source Dataset=HotpotQ...
2026.03
73.1
DynHD
Source Dataset=CSQA, M...
2026.03
68.7
TSV
Source Dataset=CSQA, M...
2026.03
65.3
TraceDet
Source Dataset=CSQA, M...
2026.03
61.5
TSV
Source Dataset=HotpotQ...
2026.03
58.5
CCS
Source Dataset=CSQA, M...
2026.03
54.5
CCS
Source Dataset=HotpotQ...
2026.03
50.1
Feedback
Search any
task
Search any
task