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

Pop-QA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Question Answering EvaluationPop-QA Cities 20
Factual Accuracy1.75
10
Question AnsweringPop-QA Cities-20
BLEU-124.2
10
Showing 2 of 2 rows