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

ToolQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Tool-based Question AnsweringToolQA hard
Accuracy (Yelp)63
17
Tool-use Question AnsweringToolQA Easy 1.0
Yelp Acc90
17
Skill retrievalToolQA
nDCG@156.4
11
Showing 3 of 3 rows