iiRecord
Agentic AI Atlas · eval-run:mmlu.o1.2024-12
eval-run:mmlu.o1.2024-12a5c.ai
II.
EvalRun JSON

eval-run:mmlu.o1.2024-12

Structured · live

eval-run:mmlu.o1.2024-12 json

Inspect the normalized record payload exactly as the atlas UI reads it.

File · benchmarks/eval-runs/eval-runs-openai.yamlCluster · benchmarks
Record JSON
{
  "id": "eval-run:mmlu.o1.2024-12",
  "_kind": "EvalRun",
  "_file": "benchmarks/eval-runs/eval-runs-openai.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "target": "model:o1@current",
    "benchmarkId": "benchmark:mmlu",
    "testSetId": "test-set:swe-bench-verified-2024-12",
    "targetId": "model:o1@current",
    "runAt": "2024-12-05T00:00:00Z",
    "runBy": "openai",
    "configHash": "sha256:placeholder-o1-mmlu"
  },
  "outgoingEdges": [
    {
      "from": "eval-run:mmlu.o1.2024-12",
      "to": "model:o1@current",
      "kind": "evaluates_target"
    },
    {
      "from": "eval-run:mmlu.o1.2024-12",
      "to": "benchmark:mmlu",
      "kind": "for_benchmark"
    }
  ],
  "incomingEdges": [
    {
      "from": "eval-result:mmlu.o1.001",
      "to": "eval-run:mmlu.o1.2024-12",
      "kind": "belongs_to_eval_run"
    }
  ]
}