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

Tool-use agent performance on MetaTool

85.9ASR (Success Rate)

MemMorph

5.40426.30247.268.098May 24, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.05
85.9
2026.05
83.8
2026.05
81.2
2026.05
79.5
2026.05
78.6
2026.05
78.6
2026.05
77.8
2026.05
77.6
2026.05
76.9
2026.05
75.2
2026.05
72.7
2026.05
72.6
2026.05
72.6
2026.05
72.6
2026.05
70.9
2026.05
70.1
2026.05
70.1
2026.05
68.4
2026.05
67.8
2026.05
63.2
2026.05
62.4
2026.05
58.1
2026.05
57.3
2026.05
57.2
2026.05
56.3
2026.05
55.6
2026.05
55.6
2026.05
55.6
2026.05
54.7
2026.05
54.4
2026.05
53
2026.05
53
2026.05
50.4
2026.05
49.6
2026.05
45.3
2026.05
44.4
2026.05
44.3
2026.05
44.1
2026.05
41.9
2026.05
35.8
2026.05
32.1
2026.05
30.7
2026.05
25.8
2026.05
25.6
2026.05
24.8
2026.05
23
2026.05
16.2
2026.05
15.4
2026.05
11.9
2026.05
8.5