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

Treasury

Benchmarks

Task NameDataset NameSOTA ResultTrend
Regressiontreasury
RMSE0.0301
12
Text Style TransferTreasury style domain
BLEU50.46
9
Faithfulness under retrainingTreasury
AURC0.118
5
Instance attribution explanationTreasury (test)
Wall-clock Time (s)0.03
4
Target sensitivity estimationTreasury (test)
Pearson r1
3
Showing 5 of 5 rows