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

TR

Benchmarks

Task NameDataset NameSOTA ResultTrend
Reward PredictionTR
MAE8.9
10
Cost PredictionTR
MAE172.4
10
Count PredictionTR
MAE13.26
9
Stethoscopic text generationTR OOD (test)
ROUGE-1 Score35.2
8
Entity LinkingTR hard 2016
Accuracy (de)62
7
Entity LinkingTR hard 2016 (test)
Score (de)64
5
Showing 6 of 6 rows