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

CommaQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multi-hop ReasoningCommaQA-E compositional
Exact Match80.8
15
Multi-hop ReasoningCommaQA-E (test)
Exact Match70
15
Showing 2 of 2 rows