{
  "id": "test-set:agentclinic-clinical-cases",
  "_kind": "TestSet",
  "_file": "benchmarks/test-sets/source-backed-benchmark-test-sets.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "AgentClinic clinical case suite",
    "benchmarkId": "benchmark:agentclinic",
    "composition": "AgentClinic's simulated clinical case suite evaluates agents through\npatient interactions, multimodal data collection, incomplete\ninformation, and tool use across medical specialties and languages.\n",
    "homepageUrl": "https://agentclinic.github.io/",
    "description": "Canonical AgentClinic artifact for multimodal clinical-agent\ndiagnostic reasoning evaluation.\n"
  },
  "outgoingEdges": [
    {
      "from": "test-set:agentclinic-clinical-cases",
      "to": "benchmark:agentclinic",
      "kind": "belongs_to_benchmark"
    }
  ],
  "incomingEdges": []
}