# MMATH: A Multilingual Benchmark for Mathematical Reasoning

arXiv: https://arxiv.org/abs/2505.19126 · HTML: https://mlsanity.com/paper/2505.19126/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Mathematical reasoning, one of 17 directions in LLM reasoning.
- Builds on 24 of its 32 references that are in the map.
- First posted on arXiv 25 May 2025.

## Placed in

- LLM reasoning / [Mathematical reasoning](https://mlsanity.com/lr/mathematical-reasoning/)

## Builds on (most cited first, 24 of 24)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Bag of Tricks for Efficient Text Classification](https://mlsanity.com/paper/1607.01759/) (2016)
- [Language Models are Multilingual Chain-of-Thought Reasoners](https://mlsanity.com/paper/2210.03057/) (2022)
- [LIMO: Less is More for Reasoning](https://mlsanity.com/paper/2502.03387/) (2025)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [Alphazero-like Tree-Search can Guide Large Language Model Decoding and Training](https://mlsanity.com/paper/2309.17179/) (2023)
- [Reasoning Models Can Be Effective Without Thinking](https://mlsanity.com/paper/2504.09858/) (2025)
- [Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond](https://mlsanity.com/paper/2503.10460/) (2025)
- [Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting](https://mlsanity.com/paper/2305.07004/) (2023)
- [Free Process Rewards without Process Labels](https://mlsanity.com/paper/2412.01981/) (2024)
- [Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers](https://mlsanity.com/paper/2408.06195/) (2024)
- [Effectively Controlling Reasoning Models through Thinking Intervention](https://mlsanity.com/paper/2503.24370/) (2025)
- [Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations](https://mlsanity.com/paper/2310.20246/) (2023)
- [PolyMath: Evaluating Mathematical Reasoning in Multilingual Contexts](https://mlsanity.com/paper/2504.18428/) (2025)
- [Linguistic Generalizability of Test-Time Scaling in Mathematical Reasoning](https://mlsanity.com/paper/2502.17407/) (2025)
- [Is Translation All You Need? A Study on Solving Multilingual Tasks with Large Language Models](https://mlsanity.com/paper/2403.10258/) (2024)
- [Comparative Analysis of Multilingual Text Classification & Identification through Deep Learning and Embedding Visualization](https://mlsanity.com/paper/2312.03789/) (2023)

## Built on by (most cited first, 17 of 17)

- [Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning](https://mlsanity.com/paper/2510.07300/) (2025)
- [SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding](https://mlsanity.com/paper/2604.09557/) (2026)
- [TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning](https://mlsanity.com/paper/2603.25419/) (2026)
- [R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and Reasoning](https://mlsanity.com/paper/2602.05940/) (2026)
- [Beg to Differ: Understanding Reasoning-Answer Misalignment Across Languages](https://mlsanity.com/paper/2512.22712/) (2025)
- [Cross-lingual Self-Consistency for Multilingual Reasoning with Language Models](https://mlsanity.com/paper/2606.01464/) (2026)
- [M3Kang: Evaluating Multilingual Multimodal Mathematical Reasoning in Vision-Language Models](https://mlsanity.com/paper/2601.16218/) (2026)
- [mAceReason-Math: A Dataset of High-Quality Multilingual Math Problems Ready For RLVR](https://mlsanity.com/paper/2603.10767/) (2026)
- [Efficient Multilingual Reasoning Transfer via Progressive Code-Switching](https://mlsanity.com/paper/2607.00485/) (2026)
- [Mind the Cap: Output-Budget Regimes Change the Measured Multilingual Reasoning Gap](https://mlsanity.com/paper/2608.04160/) (2026)
- [Multilingual Reasoning Cascades Need More Context](https://mlsanity.com/paper/2606.27306/) (2026)
- [Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAG](https://mlsanity.com/paper/2607.02966/) (2026)
- [ADAGE: A Language-Agnostic Pipeline for Analogical Reasoning Evaluation](https://mlsanity.com/paper/2607.23058/) (2026)
- [Enhancing Low-Resource Language Reasoning via High-Resource Language Feature Transfer](https://mlsanity.com/paper/2608.30462/) (2026)
- [When Tokenization is Secretly Output Supervision](https://mlsanity.com/paper/2609.01386/) (2026)
- [Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning](https://mlsanity.com/paper/2609.10445/) (2026)
- [Scaling Multilingual Safety and Reasoning Evaluation through Reasoning-Guided Translation](https://mlsanity.com/paper/2610.20221/) (2026)

## Abstract (arXiv)

The advent of large reasoning models, such as OpenAI o1 and DeepSeek R1, has significantly advanced complex reasoning tasks. However, their capabilities in multilingual complex reasoning remain underexplored, with existing efforts largely focused on simpler tasks like MGSM. To address this gap, we introduce MMATH, a benchmark for multilingual complex reasoning spanning 374 high-quality math problems across 10 typologically diverse languages. Using MMATH, we observe that even advanced models like DeepSeek R1 exhibit substantial performance disparities across languages and suffer from a critical off-target issue-generating responses in unintended languages. To address this, we explore strategies including prompting and training, demonstrating that reasoning in English and answering in target languages can simultaneously enhance performance and preserve target-language consistency. Our findings offer new insights and practical strategies for advancing the multilingual reasoning capabilities of large language models. Our code and data could be found at https://github.com/RUCAIBox/MMATH.