Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

TyDiQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multilingual Question AnsweringTydiQA
Accuracy81.9
44
Question AnsweringTyDiQA
Exact Match52.14
28
Question AnsweringTyDiQA GoldP
F1 Score89.4
20
MultilingualityTydiQA
F1 Score70.8
16
Question AnsweringTyDiQA GoldP (test)
F1 Score87.7
12
Performance PredictionTyDiQA
MAE4.29
9
Zero-shot performance predictionTyDiQA
MAE3.42
9
Hallucination DetectionTyDiQA-GP
AUC ROC0.9404
8
Question AnsweringTyDiQA
Score53.56
6
Question AnsweringTyDiQA (test)
Average Score72.4
4
Multilingual Question AnsweringTyDiQA GoldP (val)
Ar Score80
4
Showing 11 of 11 rows