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

MENT

Benchmarks

Task NameDataset NameSOTA ResultTrend
Machine Translation Meta-evaluationMENT EN-ZH
Meta Score80.4
30
Machine Translation Meta-evaluationMENT ZH-EN
Meta Score80.4
30
Entity-level factuality evaluationMENT Dataset converted
Accuracy78.48
3
Showing 3 of 3 rows