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

Tool-use decision-making on MetaTool (test)

90.2Decision Accuracy

MeCo

57.02465.63774.2582.863Feb 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.02
90.2
2025.02
89.2
2025.02
89.2
2025.02
87.3
2025.02
86.5
2025.02
86.2
2025.02
86
2025.02
86
2025.02
85.4
2025.02
85
2025.02
84.8
2025.02
84.6
2025.02
84.4
2025.02
84.3
2025.02
82.3
2025.02
82.1
2025.02
81.7
2025.02
81.2
2025.02
80.8
2025.02
80.8
2025.02
79.6
2025.02
77.7
2025.02
77.1
2025.02
75.4
2025.02
74.7
2025.02
74
2025.02
73.7
2025.02
73.1
2025.02
71.2
2025.02
69
2025.02
68.8
2025.02
68.5
2025.02
65
2025.02
63.5
2025.02
62.7
2025.02
61.9
2025.02
61.3
2025.02
58.3