# MMStar

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

Measures vision-essential multimodal capabilities using human-selected samples filtered to resist text-only solving and leakage.

## Details

- Address: Online, Global
- Website: [github.com/MMStar-Benchmark/MMStar](<https://github.com/MMStar-Benchmark/MMStar>)
- Tags: Science
- Category: Multimodal
- Status: Active
- Data licence: unknown
- Data access: open
- Grader: exact
- Organization: MMStar team
- Released: 2024-03
- Paper: [arxiv.org/abs/2403.20330](<https://arxiv.org/abs/2403.20330>)
- Leaderboard: [mmstar-benchmark.github.io/](<https://mmstar-benchmark.github.io/>)
- Repository: [github.com/MMStar-Benchmark/MMStar](<https://github.com/MMStar-Benchmark/MMStar>)
- Task count: 1,500
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is MMStar?

MMStar is at Online, Global.

### How do I contact MMStar?

To contact MMStar, visit https://github.com/MMStar-Benchmark/MMStar.

## 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/mmstar>)
- [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.