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

Natural Plan

Benchmarks

Task NameDataset NameSOTA ResultTrend
Meeting PlanningNatural Plan
Accuracy95
10
Calendar SchedulingNatural Plan Calendar Scheduling
Success Rate72
8
Meeting PlanningNatural Plan Meeting Planning
Success Rate49.8
8
Trip PlanningNatural Plan Trip Planning
Success Rate33.2
8
PlanningNatural Plan (in-distribution)
Success Rate91.7
3
PlanningNatural Plan
Trip Planning Score7.9
3
Showing 6 of 6 rows