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

GUI Agent Task Completion on WeChat Mini-App Real-World (test)

42.28Success Rate (Human)

code-native-reward (Ours)

36.695238.145139.59541.0449Feb 15, 2026
Updated 5mo ago

Evaluation Results

MethodLinks
2026.02
42.28
2026.02
41.61
2026.02
40.94
2026.02
36.91