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

Tool-use API Generalization on ToolBench G1 v1

83.5Pass Rate

EVOTOOL

45.64455.47265.375.128Mar 5, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
83.5
2026.03
82.1
2026.03
80.3
2026.03
73.5
2026.03
73.3
2026.03
72.2
2026.03
70.7
2026.03
70.1
2026.03
69.3
2026.03
68.5
2026.03
68.2
2026.03
64.5
2026.03
63.3
2026.03
62.2
2026.03
61.7
2026.03
61
2026.03
60.3
2026.03
60
2026.03
55.7
2026.03
54.7
2026.03
53.5
2026.03
47.1