# 3LM: Bridging Arabic, STEM, and Code through Benchmarking

arXiv: https://arxiv.org/abs/2507.15850 · HTML: https://mlsanity.com/paper/2507.15850/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 26 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 15 of 15)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [HumanEval-XL: A Multilingual Code Generation Benchmark for Cross-lingual Natural Language Generalization](https://mlsanity.com/paper/2402.16694/) (2024)
- [AceGPT, Localizing Large Language Models in Arabic](https://mlsanity.com/paper/2309.12053/) (2023)
- [ORCA: A Challenging Benchmark for Arabic Language Understanding](https://mlsanity.com/paper/2212.10758/) (2022)
- [AraDiCE: Benchmarks for Dialectal and Cultural Capabilities in LLMs](https://mlsanity.com/paper/2409.11404/) (2024)
- [mHumanEval -- A Multilingual Benchmark to Evaluate Large Language Models for Code Generation](https://mlsanity.com/paper/2410.15037/) (2024)
- [YourBench: Easy Custom Evaluation Sets for Everyone](https://mlsanity.com/paper/2504.01833/) (2025)
- [Jawaher: A Multidialectal Dataset of Arabic Proverbs for LLM Benchmarking](https://mlsanity.com/paper/2503.00231/) (2025)
- [Fann or Flop: A Multigenre, Multiera Benchmark for Arabic Poetry Understanding in LLMs](https://mlsanity.com/paper/2505.18152/) (2025)
- [Palm: A Culturally Inclusive and Linguistically Diverse Dataset for Arabic LLMs](https://mlsanity.com/paper/2503.00151/) (2025)
- [AraSTEM: A Native Arabic Multiple Choice Question Benchmark for Evaluating LLMs Knowledge In STEM Subjects](https://mlsanity.com/paper/2501.00559/) (2024)
- [From Guidelines to Practice: A New Paradigm for Arabic Language Model Evaluation](https://mlsanity.com/paper/2506.01920/) (2025)

## Built on by (most cited first, 5 of 5)

- [Evaluating Arabic Large Language Models: A Survey of Benchmarks, Methods, and Gaps](https://mlsanity.com/paper/2510.13430/) (2025)
- [DialectalArabicMMLU: Benchmarking Dialectal Capabilities in Arabic and Multilingual Language Models](https://mlsanity.com/paper/2510.27543/) (2025)
- [AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models](https://mlsanity.com/paper/2511.14295/) (2025)
- [Bridging the English-Arabic Medical Knowledge Gap: Targeted Low-Rank Adaptation via Causal Layer Selection](https://mlsanity.com/paper/2608.00207/) (2026)
- [AraDynFact: Dynamic Evaluation of Factual Knowledge in Arabic](https://mlsanity.com/paper/2609.35461/) (2026)

## Abstract (arXiv)

Arabic is one of the most widely spoken languages in the world, yet efforts to develop and evaluate Large Language Models (LLMs) for Arabic remain relatively limited. Most existing Arabic benchmarks focus on linguistic, cultural, or religious content, leaving a significant gap in domains like STEM and code which are increasingly relevant for real-world LLM applications. To help bridge this gap, we present 3LM, a suite of three benchmarks designed specifically for Arabic. The first is a set of STEM-related question-answer pairs, naturally sourced from Arabic textbooks and educational worksheets. The second consists of synthetically generated STEM questions, created using the same sources. The third benchmark focuses on code generation, built through a careful translation of two widely used code benchmarks, incorporating a human-in-the-loop process with several rounds of review to ensure high-quality and faithful translations. We release all three benchmarks publicly to support the growth of Arabic LLM research in these essential but underrepresented areas.