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

Tool-based Question Answering on ToolQA hard

63Accuracy (Yelp)

React

-1.4815.263248.74Dec 3, 2025
Updated 3mo ago

Evaluation Results

MethodLinks
2025.12
6314223211
2025.12
5114142410
2025.12
471413233
2025.12
431020177
2025.12
372693823
2025.12
2933101614
2025.12
2720132718
2025.12
247867
2025.12
2117181520
2025.12
161382844
2025.12
1000113
2025.12
100079
2025.12
61371429
2025.12
613267
2025.12
30074
2025.12
21341013
2025.12
10021