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

Bamb

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-Hop Question AnsweringBamb
Exact Match (EM)54.4
30
Multi-Hop Question AnsweringBamb
F1 Score (Bamb)71
17
Showing 2 of 2 rows