eval-run:mmlu.claude-sonnet-4-6.2025-11

{
  "id": "eval-run:mmlu.claude-sonnet-4-6.2025-11",
  "_kind": "EvalRun",
  "_file": "benchmarks/eval-runs/eval-runs-anthropic.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "target": "model:claude-sonnet-4-6@current",
    "benchmarkId": "benchmark:mmlu",
    "testSetId": "test-set:swe-bench-verified-2024-12",
    "targetId": "model:claude-sonnet-4-6@current",
    "runAt": "2025-11-15T00:00:00Z",
    "runBy": "anthropic",
    "configHash": "sha256:placeholder-claude-sonnet-4-6-mmlu"
  },
  "outgoingEdges": [
    {
      "from": "eval-run:mmlu.claude-sonnet-4-6.2025-11",
      "to": "model:claude-sonnet-4-6@current",
      "kind": "evaluates_target"
    },
    {
      "from": "eval-run:mmlu.claude-sonnet-4-6.2025-11",
      "to": "benchmark:mmlu",
      "kind": "for_benchmark"
    }
  ],
  "incomingEdges": [
    {
      "from": "eval-result:mmlu.claude-sonnet-4-6.001",
      "to": "eval-run:mmlu.claude-sonnet-4-6.2025-11",
      "kind": "belongs_to_eval_run"
    }
  ]
}