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

GUI Agent Task on MemGUI-Bench Medium

35.7Precision@1

M3A

-1.4288.21117.8527.489Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
35.75048.7
2026.06
35.761.952.3
2026.06
28.647.638.8
2026.06
23.833.336.5
2026.06
21.440.528.8
2026.06
1942.942.5
2026.06
16.745.2-
2026.06
14.323.822.4
2026.06
7.114.321.3
2026.06
4.814.316
2026.06
2.42.44.4
2026.06
2.42.416.5
2026.06
000
2026.06
02.40.5
2026.06
02.40
2026.06
02.45
2026.06
001.7
2026.06
001.2
2026.06
000