{
  "id": "test-set:humaneval-original",
  "_kind": "TestSet",
  "_file": "benchmarks/test-sets/source-backed-benchmark-test-sets.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "HumanEval original problem set",
    "benchmarkId": "benchmark:human-eval",
    "caseCount": 164,
    "releasedAt": "2021-07-07",
    "composition": "Hand-written Python function-completion problems for evaluating\nfunctional correctness of generated code from signatures and docstrings.\n",
    "homepageUrl": "https://github.com/openai/human-eval",
    "description": "Canonical HumanEval artifact for Python code-generation evaluation.\n"
  },
  "outgoingEdges": [
    {
      "from": "test-set:humaneval-original",
      "to": "benchmark:human-eval",
      "kind": "belongs_to_benchmark"
    }
  ],
  "incomingEdges": []
}