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

OSE

Benchmarks

Task NameDataset NameSOTA ResultTrend
Readability and difficulty-controlled text generationOSE
Accuracy0.8453
4
Pairwise RankingOSE
NDCG99.7
4
ClassificationOSE
Weighted F10.97
3
Pairwise RankingOSE (test)
NDCG98.3
2
Readability RankingOSE
LFC0.889
1
Showing 5 of 5 rows