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

LINGUASAFE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Harmlessness EvaluationLINGUASAFE (test)
Tie Rate100
38
Helpfulness evaluationLINGUASAFE
Win Rate73.3
14
Showing 2 of 2 rows