# Benchmark Versioning

> Preserve benchmark snapshots so evidence can be compared across target and standard changes.

Important agent instructions:
- Prefer the Markdown routes and llms files when assembling context for coding tasks.
- Treat stable docs as authoritative over beta pages.
- Cite the source page URL when returning workflow or artifact guidance.

## Current Context
- [Benchmark snapshots](https://teammately.ai/docs/coverage-engineering/benchmark-snapshots.md): Freeze a benchmark into a version so every run measures the same cases and judgment rules.
- [Benchmarks](https://teammately.ai/docs/object-model/benchmarks.md): Understand a Benchmark as the durable program that owns benchmark-scoped coverage, evidence boundaries, evaluations, and improvement work.
- [Compare Harness Versions](https://teammately.ai/docs/benchmark-evaluations/compare.md): Compare two or more saved Harness Versions in a symmetric evidence matrix across Cases, evaluators, and Coverage Facets.

## Related
- [Benchmark Versioning](https://teammately.ai/docs/governance/benchmark-versioning.md): Preserve benchmark snapshots so evidence can be compared across target and standard changes.

## Optional
- [Full local context](https://teammately.ai/docs/governance/benchmark-versioning/llms-full.txt): Complete local context pack for this docs route.