# ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic

arXiv: https://arxiv.org/abs/2402.12840 · HTML: https://mlsanity.com/paper/2402.12840/

## Key facts

- Cited by 88 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 40 of its 58 references that are in the map.
- First posted on arXiv 20 Feb 2024.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 40)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [XNLI: Evaluating Cross-lingual Sentence Representations](https://mlsanity.com/paper/1809.05053/) (2018)
- [The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only](https://mlsanity.com/paper/2306.01116/) (2023)
- [XTREME: A Massively Multilingual Multi-task Benchmark for Evaluating Cross-lingual Generalization](https://mlsanity.com/paper/2003.11080/) (2020)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback](https://mlsanity.com/paper/2309.00267/) (2023)
- [TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages](https://mlsanity.com/paper/2003.05002/) (2020)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [AraBERT: Transformer-based Model for Arabic Language Understanding](https://mlsanity.com/paper/2003.00104/) (2020)
- [MLQA: Evaluating Cross-lingual Extractive Question Answering](https://mlsanity.com/paper/1910.07475/) (2019)
- [Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning](https://mlsanity.com/paper/1909.00277/) (2019)
- [Few-shot Learning with Multilingual Language Models](https://mlsanity.com/paper/2112.10668/) (2021)
- [Negated and Misprimed Probes for Pretrained Language Models: Birds Can Talk, But Cannot Fly](https://mlsanity.com/paper/1911.03343/) (2019)
- [The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics](https://mlsanity.com/paper/2102.01672/) (2021)
- [XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation](https://mlsanity.com/paper/2004.01401/) (2020)
- [XTREME-R: Towards More Challenging and Nuanced Multilingual Evaluation](https://mlsanity.com/paper/2104.07412/) (2021)
- [ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic](https://mlsanity.com/paper/2101.01785/) (2020)
- [WikiLingua: A New Benchmark Dataset for Cross-Lingual Abstractive Summarization](https://mlsanity.com/paper/2010.03093/) (2020)
- [The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models](https://mlsanity.com/paper/2103.06678/) (2021)
- [LLM360: Towards Fully Transparent Open-Source LLMs](https://mlsanity.com/paper/2312.06550/) (2023)
- [AceGPT, Localizing Large Language Models in Arabic](https://mlsanity.com/paper/2309.12053/) (2023)
- [Language models are not naysayers: An analysis of language models on negation benchmarks](https://mlsanity.com/paper/2306.08189/) (2023)

## Built on by (most cited first, 30 of 88)

- [INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge](https://mlsanity.com/paper/2411.19799/) (2024)
- [ALLaM: Large Language Models for Arabic and English](https://mlsanity.com/paper/2407.15390/) (2024)
- [All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages](https://mlsanity.com/paper/2411.16508/) (2024)
- [AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs](https://mlsanity.com/paper/2409.11404/) (2024)
- [IndoCulture: Exploring Geographically-Influenced Cultural Commonsense Reasoning Across Eleven Indonesian Provinces](https://mlsanity.com/paper/2404.01854/) (2024)
- [Enhancing Multilingual LLM Pretraining with Model-Based Data Selection](https://mlsanity.com/paper/2502.10361/) (2025)
- [CaLMQA: Exploring culturally specific long-form question answering across 23 languages](https://mlsanity.com/paper/2406.17761/) (2024)
- [Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Art](https://mlsanity.com/paper/2406.03930/) (2024)
- [MEXA: Multilingual Evaluation of English-Centric LLMs via Cross-Lingual Alignment](https://mlsanity.com/paper/2410.05873/) (2024)
- [BertaQA: How Much Do Language Models Know About Local Culture?](https://mlsanity.com/paper/2406.07302/) (2024)
- [Unveiling Linguistic Regions in Large Language Models](https://mlsanity.com/paper/2402.14700/) (2024)
- [CAMEL-Bench: A Comprehensive Arabic LMM Benchmark](https://mlsanity.com/paper/2410.18976/) (2024)
- [Command R7B Arabic: A Small, Enterprise Focused, Multilingual, and Culturally Aware Arabic LLM](https://mlsanity.com/paper/2503.14603/) (2025)
- [ProverbEval: Exploring LLM Evaluation Challenges for Low-resource Language Understanding](https://mlsanity.com/paper/2411.05049/) (2024)
- [MuBench: Assessment of Multilingual Capabilities of Large Language Models Across 61 Languages](https://mlsanity.com/paper/2506.19468/) (2025)
- [Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect](https://mlsanity.com/paper/2409.17912/) (2024)
- [BenCzechMark : A Czech-centric Multitask and Multimetric Benchmark for Large Language Models with Duel Scoring Mechanism](https://mlsanity.com/paper/2412.17933/) (2024)
- [ArabLegalEval: A Multitask Benchmark for Assessing Arabic Legal Knowledge in Large Language Models](https://mlsanity.com/paper/2408.07983/) (2024)
- [CamelEval: Advancing Culturally Aligned Arabic Language Models and Benchmarks](https://mlsanity.com/paper/2409.12623/) (2024)
- [Revisiting Compositional Generalization Capability of Large Language Models Considering Instruction Following Ability](https://mlsanity.com/paper/2506.15629/) (2025)
- [Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions](https://mlsanity.com/paper/2508.08287/) (2025)
- [TUMLU: A Unified and Native Language Understanding Benchmark for Turkic Languages](https://mlsanity.com/paper/2502.11020/) (2025)
- [MultiHoax: A Dataset of Multi-hop False-Premise Questions](https://mlsanity.com/paper/2506.00264/) (2025)
- [Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps](https://mlsanity.com/paper/2510.13430/) (2025)
- [Cultural Adaptation of Menus: A Fine-Grained Approach](https://mlsanity.com/paper/2408.13534/) (2024)
- [AIN: The Arabic INclusive Large Multimodal Model](https://mlsanity.com/paper/2502.00094/) (2025)
- [A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment](https://mlsanity.com/paper/2502.13520/) (2025)
- [HKCanto-Eval: A Benchmark for Evaluating Cantonese Language Understanding and Cultural Comprehension in LLMs](https://mlsanity.com/paper/2503.12440/) (2025)
- [Alignment at Pre-training! Towards Native Alignment for Arabic LLMs](https://mlsanity.com/paper/2412.03253/) (2024)
- [JEEM: Vision-Language Understanding in Four Arabic Dialects](https://mlsanity.com/paper/2503.21910/) (2025)

## Abstract (arXiv)

The focus of language model evaluation has transitioned towards reasoning and knowledge-intensive tasks, driven by advancements in pretraining large models. While state-of-the-art models are partially trained on large Arabic texts, evaluating their performance in Arabic remains challenging due to the limited availability of relevant datasets. To bridge this gap, we present datasetname, the first multi-task language understanding benchmark for the Arabic language, sourced from school exams across diverse educational levels in different countries spanning North Africa, the Levant, and the Gulf regions. Our data comprises 40 tasks and 14,575 multiple-choice questions in Modern Standard Arabic (MSA) and is carefully constructed by collaborating with native speakers in the region. Our comprehensive evaluations of 35 models reveal substantial room for improvement, particularly among the best open-source models. Notably, BLOOMZ, mT0, LLaMA2, and Falcon struggle to achieve a score of 50%, while even the top-performing Arabic-centric model only achieves a score of 62.3%.