# M4U: Evaluating Multilingual Understanding and Reasoning for Large Multimodal Models

arXiv: https://arxiv.org/abs/2405.15638 · HTML: https://mlsanity.com/paper/2405.15638/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 9 of its 50 references that are in the map.
- First posted on arXiv 24 May 2024.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 9 of 9)

- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension](https://mlsanity.com/paper/2307.16125/) (2023)
- [Yi: Open Foundation Models by 01.AI](https://mlsanity.com/paper/2403.04652/) (2024)
- [M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning](https://mlsanity.com/paper/2306.04387/) (2023)
- [CMB: A Comprehensive Medical Benchmark in Chinese](https://mlsanity.com/paper/2308.08833/) (2023)
- [EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models](https://mlsanity.com/paper/2403.10378/) (2024)

## Built on by (most cited first, 13 of 13)

- [All Languages Matter: Evaluating LMMs on Culturally Diverse 100 Languages](https://mlsanity.com/paper/2411.16508/) (2024)
- [GEOBench-VLM: Benchmarking Vision-Language Models for Geospatial Tasks](https://mlsanity.com/paper/2411.19325/) (2024)
- [Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning](https://mlsanity.com/paper/2502.02871/) (2025)
- [Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency](https://mlsanity.com/paper/2407.09519/) (2024)
- [MultiNRC: A Challenging and Native Multilingual Reasoning Evaluation Benchmark for LLMs](https://mlsanity.com/paper/2507.17476/) (2025)
- [IndicVisionBench: Benchmarking Cultural and Multilingual Understanding in VLMs](https://mlsanity.com/paper/2511.04727/) (2025)
- [Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering](https://mlsanity.com/paper/2511.23231/) (2025)
- [Benchmarking Vision Language Models on German Factual Data](https://mlsanity.com/paper/2504.11108/) (2025)
- [M3Kang: Evaluating Multilingual Multimodal Mathematical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2601.16218/) (2026)
- [MSA at ImageCLEF 2025 Multimodal Reasoning: Multilingual Multimodal Reasoning With Ensemble Vision Language Models](https://mlsanity.com/paper/2507.11114/) (2025)
- [Can you SPLICE it together? A Human Curated Benchmark for Probing Visual Reasoning in VLMs](https://mlsanity.com/paper/2509.24640/) (2025)
- [TimeSpot: Benchmarking Geo-Temporal Understanding in Vision-Language Models in Real-World Settings](https://mlsanity.com/paper/2603.06687/) (2026)
- [The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes](https://mlsanity.com/paper/2606.11470/) (2026)

## Abstract (arXiv)

Multilingual capability is an essential aspect for large multimodal models, since they are usually deployed across various countries and languages. However, most existing benchmarks for multilingual multimodal reasoning struggle to differentiate between models of varying performance; even language models without visual capabilities can easily achieve high scores. This leaves a comprehensive evaluation of leading multilingual multimodal models largely unexplored. In this work, we introduce M4U, a novel and challenging benchmark for assessing the capability of multi-discipline multilingual multimodal understanding and reasoning. M4U contains 10k samples covering 64 disciplines across 16 subfields in Science, Engineering, and Healthcare in six languages. Using M4U, we conduct extensive evaluations of leading Large Multimodal Models (LMMs) and Large Language Models (LLMs) with external tools. The evaluation results demonstrate that the state-of-the-art model, GPT-4o, achieves only 47.6% average accuracy on M4U. Additionally, we observe that the leading LMMs exhibit significant language preferences. Our in-depth analysis indicates that leading LMMs, including GPT-4o, struggle to perform reasoning using multilingual information present in both visual and textual context. Specifically, they suffer performance degradation when prompted with cross-lingual multimodal questions. Our code and dataset is public available.