# MLPerf Inference

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

Measures how quickly and efficiently hardware and software systems run trained models across deployment scenarios.

## Details

- Address: Online, Global
- Website: [github.com/mlcommons/inference](<https://github.com/mlcommons/inference>)
- Tags: Science, Helpful
- Category: Other
- Status: Active
- Data licence: Apache-2.0
- Data access: open
- Grader: exact
- Organization: MLCommons
- Released: 2019-11
- Paper: [arxiv.org/abs/1911.02549](<https://arxiv.org/abs/1911.02549>)
- Leaderboard: [mlcommons.org/benchmarks/inference-datacenter/](<https://mlcommons.org/benchmarks/inference-datacenter/>)
- Repository: [github.com/mlcommons/inference](<https://github.com/mlcommons/inference>)
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is MLPerf Inference?

MLPerf Inference is at Online, Global.

### How do I contact MLPerf Inference?

To contact MLPerf Inference, visit https://github.com/mlcommons/inference.

## 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/mlperf-inference>)
- [Other in Online](<https://aibenchmarkindex.com/global/online/category/other.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.