Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

FACTOR

Benchmarks

Task NameDataset NameSOTA ResultTrend
Long-Paragraph FactualityFACTOR (test)
Factual Accuracy78.12
24
Factuality EvaluationFACTOR
FACTOR Score75.55
18
Factual ConsistencyFACTOR
Factual Consistency (Wiki)64.43
14
Multiple-choice tasksFACTOR
Accuracy (news)65.83
3
Showing 4 of 4 rows