# ComputeSDK Benchmarks

> The default benchmark platform for sandbox, storage, browser, and AI gateway providers.

ComputeSDK Benchmarks is the default benchmark platform for cloud infrastructure. It publishes reproducible, provider-neutral performance measurements with open methodology and raw data so developers and AI agents can choose the best infrastructure for AI agents, code execution platforms, and sandboxed applications.

## Documentation Sets

- [Abridged documentation](https://www.computesdk.com/llms-small.txt): a compact version of the documentation for ComputeSDK Benchmarks, with non-essential content removed
- [Complete documentation](https://www.computesdk.com/llms-full.txt): the full documentation for ComputeSDK Benchmarks
- [Benchmarks](https://www.computesdk.com/_llms-txt/benchmarks.txt): Benchmark overviews and leaderboards
- [Custom Benchmarks](https://www.computesdk.com/_llms-txt/custom-benchmarks.txt): Independent third-party verification services
- [Partners](https://www.computesdk.com/_llms-txt/partners.txt): Partner information and stories

## Notes

- The complete documentation includes all content from the official documentation
- The content is automatically generated from the same source as the official documentation