Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Tool Calling on ToolBench generalization dataset (I2-Cat)

51.96SoPR

ToolGen*

17.775226.650135.52544.3999Jan 29, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
51.9637.9-
2026.01
46.5154.81-
2026.01
46.2435.48-
2026.01
45.5637.9-
2026.01
45.4344.35-
2026.01
39.3842.74-
2026.01
19.0920.16-
2026.01
--51.9
2026.01
--48.3
2026.01
--51.6
2026.01
--57.9
2026.01
--51.9
2026.01
--60.2