# AI Benchmark Index

> Find AI benchmarks with traceable data, licences, and scores.

AI Benchmark Index catalogs 264 AI benchmarks with source-linked facts about data, grading, and reported scores.

## Benchmarks by city

- [Online, Global, United States](https://aibenchmarkindex.com/global/online.md): 264 benchmarks

## Guides

- [How to choose an AI benchmark](https://aibenchmarkindex.com/guides/how-to-choose-an-ai-benchmark.md): Choose an AI benchmark by defining the decision first, then checking task fit, grader validity, data access, saturation, and provenance.
- [How to run an AI benchmark yourself for under $20](https://aibenchmarkindex.com/guides/run-a-benchmark-under-20.md): Keep an AI benchmark run under $20 by fixing the question, sampling tasks, estimating tokens, using deterministic graders, and saving a reproducible run record.
- [Silly benchmarks that tell you something real (pelican, skateboard, and friends)](https://aibenchmarkindex.com/guides/silly-benchmarks-real-signals.md): Playful tasks such as drawing a pelican on a bicycle can expose planning, geometry, tool use, and persistence when their grader makes the signal explicit.
- [What a saturated benchmark is and how to spot one](https://aibenchmarkindex.com/guides/what-is-a-saturated-benchmark.md): A saturated benchmark no longer separates strong systems well; spot it by score clustering, ceiling effects, stale tasks, and shrinking uncertainty-aware gaps.
- [Where benchmark data comes from and what its licence lets you do](https://aibenchmarkindex.com/guides/where-benchmark-data-comes-from.md): Benchmark data may be written, sampled, generated, or drawn from public datasets; its licence determines whether you may download, modify, and redistribute it.

> **Check before you compare.** Benchmark methods and leaderboards change. Follow the cited primary source before using a result in a decision.