# MMBench

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

Measures broad multimodal model capabilities with multiple-choice questions spanning 20 ability dimensions.

## Details

- Address: Online, Global
- Website: [github.com/open-compass/MMBench](<https://github.com/open-compass/MMBench>)
- Tags: Science
- Category: Multimodal
- Status: Active
- Data licence: Apache-2.0
- Data access: open
- Grader: exact
- Organization: OpenCompass
- Released: 2023-07
- Paper: [arxiv.org/abs/2307.06281](<https://arxiv.org/abs/2307.06281>)
- Leaderboard: [mmbench.opencompass.org.cn/](<https://mmbench.opencompass.org.cn/>)
- Repository: [github.com/open-compass/MMBench](<https://github.com/open-compass/MMBench>)
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is MMBench?

MMBench is at Online, Global.

### How do I contact MMBench?

To contact MMBench, visit https://github.com/open-compass/MMBench.

## 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/mmbench>)
- [Multimodal in Online](<https://aibenchmarkindex.com/global/online/category/multimodal.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.