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

Web-based Agent QA on WebWalkerQA

73.53Pass@1

Agent KB

34.498844.631954.76564.8981Oct 16, 2025Nov 4, 2025Nov 23, 2025Dec 12, 2025Dec 31, 2025Jan 19, 2026Feb 8, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
73.53
2026.02
73.53
2026.02
71.18
2026.02
70.59
2026.02
69.41
2026.02
68.82
2026.02
64.71
2026.02
60.64
2026.02
60.59
2026.02
58.82
2026.02
58.23
2026.02
57.64
2026.02
52.35
2025.10
45.7
2025.10
44.7
2025.10
43.5
2025.10
41.2
2025.10
39.9
2025.10
38.4
2025.10
36