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

UltraTool

Benchmarks

Task NameDataset NameSOTA ResultTrend
PlanningUltraTool (test)
n-F172.81
24
Tool-use ExecutionUltraTool first 100 queries adapted for execution (test)
Execution Success Rate82
11
Showing 2 of 2 rows