List your company

ResearchFormerly WizWand

MagicEval-Plan

Benchmarks

TaskDatasetSOTA resultTrendResults

Hierarchical Task Decomposition

MagicEval-Plan Context Inheritance 3

97.6Step Score

14

Hierarchical Task Decomposition

MagicEval-Plan Condition 3

97.5Step Count

14

Hierarchical Task Decomposition

MagicEval-Plan Dependency 3

16Step Count

14

Hierarchical Task Decomposition

MagicEval-Plan General 3

35.1Step Count

14