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

Web Agent Navigation on Mind2Web (Cross-Website)

46.1Execution Accuracy (EA)

ReasoningBank

38.8240.7142.644.49Sep 29, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
46.154.836.93.8
2025.09
44.352.633.92.3
2025.09
41.947.934.82.3
2025.09
41.851.2353.2
2025.09
41.249.834.83.4
2025.09
40.34632.11.9
2025.09
39.845.131.71.7
2025.09
39.142.231.72.1