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

Web Agent QA on WebWalkerQA

11.5F1 (Easy)

ReAct + GraphPO

5.9887.4198.8510.281Sep 25, 2025Nov 8, 2025Dec 22, 2025Feb 4, 2026Mar 20, 2026May 3, 2026Jun 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
11.513.712.312.7
2025.09
11.414.810.312.4
2025.09
11.115.510.812.8
2026.06
10.712.311.611.7
2025.09
9.511.37.49.5
2026.06
9.511.711.411.3
2025.09
9.413.39.411
2025.09
9.311.811.911.2
2025.09
8.911.411.610.9
2026.06
8.711.510.710.6
2025.09
89.25.67.6
2026.06
7.79.45.57.8
2025.09
6.29.45.87.4