- dataset:
    id: cais/hle                  # Required. Hub dataset ID (must be a Benchmark)
    task_id: default              # Required. ID of the Task, as defined in the dataset's eval.yaml
    revision: hash                # Optional. Dataset revision hash
  value: 20.90                    # Required. Metric value
  verifyToken: this_token            # Optional. Cryptographic proof of auditable evaluation
  date: "2025-01-15"              # Optional. ISO-8601 date or datetime of when the eval was run (defaults to git commit time)
  source:                         # Optional. Attribution for this result, for instance a repo containing output traces or a Paper
    url: https://huggingface.co/spaces/SaylorTwift/smollm3-mmlu-pro  # Required if source provided
    name: Eval traces             # Optional. Display name
    user: SaylorTwift             # Optional. HF username/org
  notes: "no-tools"               # Optional. Details about the evaluation setup (e.g., "tools", "no-tools", etc.)