List your company

ResearchFormerly WizWand

Tool-use Planning

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

ToolBench Average over all sets

86.54Win Rate

13

Feb 26, 2026

ToolBench G3-Instruction

0.937Win Rate

13

Feb 26, 2026

ToolBench G2-Category

78.78Win Rate

13

Feb 26, 2026

ToolBench G2-Instruction

87.59Win Rate

13

Feb 26, 2026