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

Integration

Benchmarks

Task NameDataset NameSOTA ResultTrend
Compositional GeneralizationIntegration
P1 Score49
6
Agentic Workflow AutomationIntegration domain
Overall Success Rate ($P_t$)83.3
3
Showing 2 of 2 rows