> ## Documentation Index
> Fetch the complete documentation index at: https://agent-compass.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Documentation Update

Document Benchmark-owned behavior, compatibility, parameters, commands, and outputs.

Create or update this page and its localized counterpart. It should let users run the Benchmark without reading its source:

```text theme={"system"}
docs/en/user_guide/modules/benchmarks/<benchmark-id>.mdx
```

Follow the shared [documentation contribution guide](/en/developer_guide/contributing/documentation) for page placement, localization, navigation, links, and validation.

## Required Content

Document:

* Purpose and official source links.
* Supported dataset and evaluator versions with pinned revisions.
* Task count, categories or splits, task browser, license and access requirements.
* Prerequisites, optional dependencies, task images and credentials.
* Recommended official Harness and other compatible Harnesses.
* Supported Environments and provider-specific behavior inferred by Recipes.
* Benchmark-specific parameters, defaults, valid values and selection guidance.
* Benchmark-specific metric contract: the primary metric, every metric kind, and Benchmark-owned semantics.
* Benchmark-specific output and diagnostic metadata.
* One real smoke command and one complete evaluation command.
* Known compatibility constraints and official-alignment notes.

## Keep the Page Benchmark-Specific

* Link generic parameter placement to the [shared Benchmark fields](/en/user_guide/modules/benchmarks/overview#shared-benchmark-fields), and link repeated-attempt metric semantics and aggregation behavior to [Metrics and Aggregation](/en/user_guide/other_features/results/metrics_aggregation).
* Keep `k` and strategy out of Benchmark parameter tables. Put their CLI flags in commands only when the example needs repeated attempts.
* Link Harness installation, step limits, cost tracking, command timeouts, and Model settings to Harness pages.
* Do not describe the positional Model ID as a Benchmark parameter.
* State whether each metric is binary or scalar, but do not repeat generic `pass@k` or `avg@k` definitions.
* Omit command parameters whose defaults already produce the intended run.
* Label the upstream alignment path **Recommended Harness** and alternatives **Other optional Harnesses**.
* Give every alternative Harness a complete evaluation command, not a command fragment.

Commands must be copyable and use environment-variable references for credentials and Model configuration. Explain
which image, workspace, resource, and network fields Recipes infer so users do not copy redundant parameters.

## Preview and Validate

Add the page to `docs/docs.json`, keep locale paths symmetric unless maintainers approve staged localization, preview it,
and validate it:

```bash theme={"system"}
cd docs
mint dev
mint broken-links
mint validate
```