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

Tool-calling on Stable Toolbench I3-Inst

68.85Pass Rate

ParaTool

27.66638.35849.0559.742May 28, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.05
68.8573.77
2026.05
65.5768.85
2026.05
65.5768.85
2026.05
65.5770.49
2026.05
63.9355.74
2026.05
60.6657.38
2026.05
60.6662.3
2026.05
58.82-
2026.05
57.3855.74
2026.05
52.46-
2026.05
52.4655.74
2026.05
50.8252.46
2026.05
50.8254.1
2026.05
47.5444.26
2026.05
31.3327.87
2026.05
29.2521.31