> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/cuvs/_mcp/server. # Benchmarking Guide Use these guides to compare vector-search algorithms fairly and run reproducible benchmark workflows with cuVS Bench. - [Methodologies](/user-guide/benchmarking-guide/methodologies): compare indexes using quality buckets, Pareto curves, and consistent build and search metrics. - [cuVS Bench Tool](/user-guide/benchmarking-guide/cu-vs-bench-tool): use cuVS Bench to run reproducible benchmark workflows, prepare datasets, and extend benchmark backends. ## Docs - [Methodologies](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/methodologies.md) - [cuVS Bench Tool](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool.md) - [Introduction](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/introduction.md) - [Installation](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/installation.md) - [Usage](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/usage.md) - [Datasets](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/datasets.md) - [Synthetic Dataset Generation](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/synthetic-dataset-generation.md) - [Backends](https://docs.nvidia.com/cuvs/user-guide/benchmarking-guide/cu-vs-bench-tool/backends.md)