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

Utility Evaluation on AgentDojo

78.4Utility

GLM-4.5

5.18424.19243.262.208Sep 26, 2025
Updated 3mo ago

Evaluation Results

MethodLinks
2025.09
78.4
2025.09
75.8
2025.09
72
2025.09
71.5
2025.09
69.9
2025.09
68.1
2025.09
67.9
2025.09
67.9
2025.09
65.7
2025.09
52.4
2025.09
50.9
2025.09
41.7
2025.09
38.3
2025.09
35.2
2025.09
35
2025.09
33.9
2025.09
31.9
2025.09
29.8
2025.09
28.3
2025.09
27.5
2025.09
24.4
2025.09
22.9
2025.09
19.6
2025.09
18.8
2025.09
18.5
2025.09
16.5
2025.09
16.2
2025.09
15.9
2025.09
14.7
2025.09
11.1
2025.09
9
2025.09
8