# ArabicMMLU

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

Evaluates Arabic language understanding across 40 school-exam tasks from countries in North Africa, the Levant, and the Gulf.

## Details

- Address: Online, Global
- Website: [github.com/mbzuai-nlp/ArabicMMLU](<https://github.com/mbzuai-nlp/ArabicMMLU>)
- Tags: Helpful, Science
- Category: Reasoning
- Status: Active
- Data licence: CC-BY-NC-SA-4.0
- Data access: open
- Grader: exact
- Organization: MBZUAI
- Released: 2024-02
- Paper: [arxiv.org/abs/2402.12840](<https://arxiv.org/abs/2402.12840>)
- Repository: [github.com/mbzuai-nlp/ArabicMMLU](<https://github.com/mbzuai-nlp/ArabicMMLU>)
- Task count: 14,575
- Top-score provenance: unknown
- ABI family: No

## Questions

### Where is ArabicMMLU?

ArabicMMLU is at Online, Global.

### How do I contact ArabicMMLU?

To contact ArabicMMLU, visit https://github.com/mbzuai-nlp/ArabicMMLU.

## 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/arabicmmlu>)
- [Reasoning in Online](<https://aibenchmarkindex.com/global/online/category/reasoning.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.