Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Behavior selection on BiPO (test)

64Hallucination Pair Accuracy

COLD-FD

42.1647.8353.559.17Mar 6, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
647049524950
2026.03
61-49-50-
2026.03
608154545853
2026.03
585851514545
2026.03
585849495050
2026.03
575749495050
2026.03
575849495050
2026.03
565650505050
2026.03
525649495050
2026.03
46-71-50-
2026.03
434360604949
2026.03
433954525250
2026.03
434357564847
2026.03
434360604949