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

GUI Agent Task on MemGUI-Bench (Overall)

37.5Precision@1

MemGUI-Agent-235B

-1.58.62518.7528.875Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
37.562.546.8
2026.06
32.847.739.3
2026.06
27.349.239.5
2026.06
24.246.930
2026.06
23.436.729.2
2026.06
23.435.930.2
2026.06
22.742.229.6
2026.06
20.33225
2026.06
11.715.615.5
2026.06
10.920.318.4
2026.06
9.420.315.1
2026.06
6.210.25.7
2026.06
5.510.22.4
2026.06
5.57.82.6
2026.06
3.13.90
2026.06
3.19.41.5
2026.06
3.16.23.8
2026.06
2.35.50.2
2026.06
000