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

Visual Reasoning on AgentVista

28.81Success Rate

AUTOMMEMO

5.004411.184717.36523.5453May 16, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2026.05
28.81
2026.05
23.44
2026.05
21.75
2026.05
20.03
2026.05
17.87
2026.05
17.33
2026.05
14.36
2026.05
11.7
2026.05
11.43
2026.05
11.12
2026.05
10.95
2026.05
10.86
2026.05
10.52
2026.05
10.47
2026.05
10.24
2026.05
9.72
2026.05
9.47
2026.05
9.41
2026.05
9.13
2026.05
9.05
2026.05
8.37
2026.05
7.84
2026.05
7.62
2026.05
5.92