Model datasets

Financial Agent Workflow Benchmark

12 offline workflow tasks testing constrained API use, missing information and budgets. Development-only.

{
  "id": "financial_agent_workflow_benchmark",
  "version": "0.1.0",
  "title": "Financial Agent Workflow Benchmark",
  "description": "12 offline workflow tasks testing constrained API use, missing information and budgets. Development-only.",
  "synthetic": true,
  "status": "draft",
  "release_approved": false,
  "terms": null,
  "price": null,
  "purchasable": false,
  "payment_environment": "test",
  "channels": []
}