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

Tool-calling on Stable Toolbench I2-Inst

77.42Pass Rate

ParaTool

40.520850.100459.6869.2596May 28, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.05
77.4279.03
2026.05
74.1975
2026.05
70.7567.92
2026.05
69.3573.39
2026.05
68.5563.71
2026.05
68.5570.16
2026.05
66.9863.2
2026.05
65.3264.52
2026.05
6561.29
2026.05
62.164.52
2026.05
59.6862.9
2026.05
58.06-
2026.05
54.8462.1
2026.05
51-
2026.05
44.3547.58
2026.05
41.9438.71