# MS MARCO

MS MARCO is an AI benchmark; this page records what it measures and traces its data, grader, and scores to primary sources.

Evaluates machine reading, answer generation, and passage or document ranking using questions sampled from Bing search.

## Details

- Address: Online, Global
- Website: [microsoft.github.io/msmarco/](<https://microsoft.github.io/msmarco/>)
- Tags: Helpful, Science
- Category: Retrieval
- Status: Active
- Data licence: unknown
- Data access: open
- Grader: exact
- Organization: Microsoft
- Released: 2016-11
- Paper: [arxiv.org/abs/1611.09268](<https://arxiv.org/abs/1611.09268>)
- Leaderboard: [microsoft.github.io/msmarco/](<https://microsoft.github.io/msmarco/>)
- Repository: [github.com/microsoft/msmarco](<https://github.com/microsoft/msmarco>)
- Task count: 1,010,916
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is MS MARCO?

MS MARCO is at Online, Global.

### How do I contact MS MARCO?

To contact MS MARCO, visit https://microsoft.github.io/msmarco/.

## Source

From [Benchmark primary sources](https://aibenchmarkindex.com/about), license CC0-1.0, checked 2026-10-15.

Last updated October 15, 2026.

## Links

- This benchmark on the [web page](<https://aibenchmarkindex.com/global/online/ms-marco>)
- [Retrieval in Online](<https://aibenchmarkindex.com/global/online/category/retrieval.md>)
- [More benchmarks in Online](<https://aibenchmarkindex.com/global/online.md>)

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