# BnMMLU: Measuring Massive Multitask Language Understanding in Bengali

arXiv: https://arxiv.org/abs/2505.18951 · HTML: https://mlsanity.com/paper/2505.18951/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 25 May 2025.

## Builds on (most cited first, 17 of 17)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data](https://mlsanity.com/paper/1911.00359/) (2019)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation](https://mlsanity.com/paper/2004.01401/) (2020)
- [Language Model Tokenizers Introduce Unfairness Between Languages](https://mlsanity.com/paper/2305.15425/) (2023)
- [ChatGPT Beyond English: Towards a Comprehensive Evaluation of Large Language Models in Multilingual Learning](https://mlsanity.com/paper/2304.05613/) (2023)
- [A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languages](https://mlsanity.com/paper/2006.06202/) (2020)
- [KMMLU: Measuring Massive Multitask Language Understanding in Korean](https://mlsanity.com/paper/2402.11548/) (2024)
- [ArabicMMLU: Assessing Massive Multitask Language Understanding in Arabic](https://mlsanity.com/paper/2402.12840/) (2024)
- [M3KE: A Massive Multi-Level Multi-Subject Knowledge Evaluation Benchmark for Chinese Large Language Models](https://mlsanity.com/paper/2305.10263/) (2023)
- [TigerLLM - A Family of Bangla Large Language Models](https://mlsanity.com/paper/2503.10995/) (2025)
- [TituLLMs: A Family of Bangla LLMs with Comprehensive Benchmarking](https://mlsanity.com/paper/2502.11187/) (2025)
- [BanglaQuAD: A Bengali Open-domain Question Answering Dataset](https://mlsanity.com/paper/2410.10229/) (2024)
- [Pralekha: Cross-Lingual Document Alignment for Indic Languages](https://mlsanity.com/paper/2411.19096/) (2024)

## Built on by (most cited first, 7 of 7)

- [Cross-Lingual Sentiment Misalignment: Auditing Multilingual Language Models for Inversion Risk, Dialectal Representation, and Affective Stability](https://mlsanity.com/paper/2602.17469/) (2026)
- [CRaFT: An Explanation-Based Framework for Evaluating Cultural Reasoning in Multilingual Language Models](https://mlsanity.com/paper/2510.14014/) (2025)
- [BengaliMoralBench: A Benchmark for Auditing Moral Reasoning in Large Language Models within Bengali Language and Culture](https://mlsanity.com/paper/2511.03180/) (2025)
- [BanglaSocialBench: A Benchmark for Evaluating Sociopragmatic and Cultural Alignment of LLMs in Bangladeshi Social Interaction](https://mlsanity.com/paper/2603.15949/) (2026)
- [BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali](https://mlsanity.com/paper/2605.31483/) (2026)
- [PhysicsMate: A Curriculum-Grounded Bengali Benchmark for Secondary Physics QA with Small-Model Adaptation](https://mlsanity.com/paper/2610.00664/) (2026)
- [BANGLAPLAN: A Benchmark for Constraint-Based Planning and Decision-Making in Bangla](https://mlsanity.com/paper/2610.19704/) (2026)

## Abstract (arXiv)

Large-scale multitask benchmarks have driven rapid progress in language modeling, yet most emphasize high-resource languages such as English, leaving Bengali underrepresented. We present BnMMLU, a comprehensive benchmark for measuring massive multitask language understanding in Bengali. BnMMLU spans 41 domains across STEM, humanities, social sciences, and general knowledge, and contains 134,375 multiple-choice question-option pairs--the most extensive Bengali evaluation suite to date. The dataset preserves mathematical content via MathML, and includes BnMMLU-HARD, a compact subset constructed from questions most frequently missed by top systems to stress difficult cases. We benchmark 24 model variants across 11 LLM families, spanning open-weights general/multilingual, Bengali-centric open-weights, and proprietary models, covering multiple parameter scales and instruction-tuned settings. We evaluate models under standardized protocols covering two prompting styles (Direct vs. Chain-of-Thought) and two context regimes (0-shot vs. 5-shot), reporting accuracy consistently across families. Our analysis highlights persistent gaps in reasoning and application skills and indicates sublinear returns to scale across model sizes. We release the dataset and evaluation templates to support rigorous, reproducible assessment of Bengali language understanding and to catalyze progress in multilingual NLP.