# Video-MME

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

Evaluates multimodal models on short, medium, and long videos across visual domains, durations, and subtitle settings.

## Details

- Address: Online, Global
- Website: [video-mme.github.io/](<https://video-mme.github.io/>)
- Tags: Helpful, Science
- Category: Multimodal
- Status: Active
- Data licence: unknown
- Data access: open
- Grader: exact
- Organization: Video-MME team
- Released: 2024-05
- Paper: [arxiv.org/abs/2405.21075](<https://arxiv.org/abs/2405.21075>)
- Leaderboard: [video-mme.github.io/home\_page.html\#leaderboard](<https://video-mme.github.io/home_page.html#leaderboard>)
- Repository: [github.com/MME-Benchmarks/Video-MME](<https://github.com/MME-Benchmarks/Video-MME>)
- Task count: 2,700
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is Video-MME?

Video-MME is at Online, Global.

### How do I contact Video-MME?

To contact Video-MME, visit https://video-mme.github.io/.

## 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/video-mme>)
- [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.