{
  "id": "benchmark:bbh",
  "_kind": "Benchmark",
  "_file": "benchmarks/benchmarks/benchmarks-reasoning.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "BIG-Bench Hard (BBH)",
    "homepageUrl": "https://github.com/suzgunmirac/BIG-Bench-Hard",
    "kind": "reasoning",
    "targetsKind": "ModelVersion",
    "description": "23 challenging tasks from BIG-Bench where prior LLMs underperformed\naverage human raters; widely used as a model reasoning benchmark.\n"
  },
  "outgoingEdges": [
    {
      "from": "benchmark:bbh",
      "to": "skill-area:general-knowledge-reasoning",
      "kind": "covers",
      "attributes": {
        "attributes": {
          "coverage": "partial",
          "weight": 0.4
        }
      }
    },
    {
      "from": "benchmark:bbh",
      "to": "domain:computer-science",
      "kind": "applies_to",
      "attributes": {}
    }
  ],
  "incomingEdges": []
}