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

Recall-intensive tasks (SWDE, SQuAD, TQA, NQ, Drop)

Benchmarks

Task NameDataset NameSOTA ResultTrend
Recall-intensive Question AnsweringRecall-intensive tasks (SWDE, SQuAD, TQA, NQ, Drop) truncated to 2K tokens (test)
SWDE56.1
5
Showing 1 of 1 rows