iiRecord
Agentic AI Atlas · Multilingual MMLU (mMMLU)
benchmark:m-mmlua5c.ai
II.
Benchmark JSON

benchmark:m-mmlu

Structured · live

Multilingual MMLU (mMMLU) json

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

File · benchmarks/benchmarks/benchmarks-knowledge.yamlCluster · benchmarks
Record JSON
{
  "id": "benchmark:m-mmlu",
  "_kind": "Benchmark",
  "_file": "benchmarks/benchmarks/benchmarks-knowledge.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "Multilingual MMLU (mMMLU)",
    "homepageUrl": "https://huggingface.co/datasets/openai/MMMLU",
    "kind": "model-only",
    "targetsKind": "ModelVersion",
    "description": "A multilingual translation of MMLU (Massive Multitask Language\nUnderstanding) covering 14 languages, used for evaluating cross-\nlingual knowledge and reasoning. Released by OpenAI as MMMLU.\n"
  },
  "outgoingEdges": [
    {
      "from": "benchmark:m-mmlu",
      "to": "skill-area:general-knowledge-reasoning",
      "kind": "covers",
      "attributes": {}
    },
    {
      "from": "benchmark:m-mmlu",
      "to": "domain:education",
      "kind": "applies_to",
      "attributes": {}
    }
  ],
  "incomingEdges": []
}