{
  "id": "benchmark:gaia",
  "_kind": "Benchmark",
  "_file": "benchmarks/benchmarks/gaia.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "GAIA",
    "homepageUrl": "https://huggingface.co/gaia-benchmark",
    "kind": "agent-reasoning",
    "targetsKind": "AgentVersion",
    "description": "General AI Assistants benchmark — real-world agent reasoning tasks.\n"
  },
  "outgoingEdges": [
    {
      "from": "benchmark:gaia",
      "to": "skill-area:agentic-loops",
      "kind": "covers",
      "attributes": {
        "attributes": {
          "coverage": "partial",
          "weight": 0.6
        }
      }
    }
  ],
  "incomingEdges": [
    {
      "from": "eval-result:gaia.claude-code.001",
      "to": "benchmark:gaia",
      "kind": "scored_against",
      "attributes": {}
    },
    {
      "from": "eval-run:gaia.claude-code.2025",
      "to": "benchmark:gaia",
      "kind": "for_benchmark"
    },
    {
      "from": "eval-run:gaia.claude-code.2025",
      "to": "benchmark:gaia",
      "kind": "evaluated_by",
      "attributes": {}
    },
    {
      "from": "test-set:gaia-validation",
      "to": "benchmark:gaia",
      "kind": "split_of",
      "attributes": {}
    },
    {
      "from": "scope-boundary:gaia.scope",
      "to": "benchmark:gaia",
      "kind": "bounds_subject"
    }
  ]
}