# Video-MMMU

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

Measures whether multimodal models acquire and apply new knowledge from professional lecture videos.

## Details

- Address: Online, Global
- Website: [videommmu.github.io/](<https://videommmu.github.io/>)
- Tags: Helpful, Science
- Category: Multimodal
- Status: Active
- Data licence: unknown
- Data access: open
- Grader: exact
- Organization: EvolvingLMMs-Lab
- Released: 2025-01
- Paper: [arxiv.org/abs/2501.13826](<https://arxiv.org/abs/2501.13826>)
- Leaderboard: [videommmu.github.io/](<https://videommmu.github.io/>)
- Repository: [github.com/EvolvingLMMs-Lab/VideoMMMU](<https://github.com/EvolvingLMMs-Lab/VideoMMMU>)
- Task count: 900
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is Video-MMMU?

Video-MMMU is at Online, Global.

### How do I contact Video-MMMU?

To contact Video-MMMU, visit https://videommmu.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-mmmu>)
- [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.