# MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models

arXiv: https://arxiv.org/abs/2504.05782 · HTML: https://mlsanity.com/paper/2504.05782/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 20 of its 56 references that are in the map.
- First posted on arXiv 8 Apr 2025.

## 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, 20 of 20)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (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-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling](https://mlsanity.com/paper/2412.05271/) (2024)
- [Gemini: A Family of Highly Capable Multimodal Models](https://mlsanity.com/paper/2312.11805/) (2023)
- [Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking](https://mlsanity.com/paper/2403.09629/) (2024)
- [Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization](https://mlsanity.com/paper/2411.10442/) (2024)
- [Can MLLMs Reason in Multimodality? EMMA: An Enhanced MultiModal ReAsoning Benchmark](https://mlsanity.com/paper/2501.05444/) (2025)
- [DPO Meets PPO: Reinforced Token Optimization for RLHF](https://mlsanity.com/paper/2404.18922/) (2024)
- [Levels of AGI for Operationalizing Progress on the Path to AGI](https://mlsanity.com/paper/2311.02462/) (2023)
- [SEED-Story: Multimodal Long Story Generation with Large Language Model](https://mlsanity.com/paper/2407.08683/) (2024)
- [MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models](https://mlsanity.com/paper/2409.00147/) (2024)
- [A Survey on Evaluation of Multimodal Large Language Models](https://mlsanity.com/paper/2408.15769/) (2024)
- [EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models](https://mlsanity.com/paper/2403.10378/) (2024)
- [OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation](https://mlsanity.com/paper/2411.18499/) (2024)
- [A Survey on Multimodal Benchmarks: In the Era of Large AI Models](https://mlsanity.com/paper/2409.18142/) (2024)
- [Dynamic Multimodal Evaluation with Flexible Complexity by Vision-Language Bootstrapping](https://mlsanity.com/paper/2410.08695/) (2024)
- [A Systematic Review on Prompt Engineering in Large Language Models for K-12 STEM Education](https://mlsanity.com/paper/2410.11123/) (2024)

## Built on by (most cited first, 15 of 15)

- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models](https://mlsanity.com/paper/2509.25373/) (2025)
- [Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models](https://mlsanity.com/paper/2505.18536/) (2025)
- [OmniEarth-Bench: Towards Holistic Evaluation of Earth's Six Spheres and Cross-Spheres Interactions with Multimodal Observational Earth Data](https://mlsanity.com/paper/2505.23522/) (2025)
- [Seeing is Not Reasoning: MVPBench for Graph-based Evaluation of Multi-path Visual Physical CoT](https://mlsanity.com/paper/2505.24182/) (2025)
- [RoboRouter: Training-Free Policy Routing for Robotic Manipulation](https://mlsanity.com/paper/2603.07892/) (2026)
- [LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations?](https://mlsanity.com/paper/2605.26781/) (2026)
- [K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs](https://mlsanity.com/paper/2605.09635/) (2026)
- [OmniMapBench: Benchmarking Visual-Centric Reasoning on Diverse Map Documents](https://mlsanity.com/paper/2607.09068/) (2026)
- [Unified Hallucination Fuzzing for Multimodal Large Language Models](https://mlsanity.com/paper/2608.07525/) (2026)
- [MatPhaseBench: A Semantics-Guided Benchmark for Materials Phase Diagrams Understanding](https://mlsanity.com/paper/2607.02934/) (2026)
- [Improving Generalization Robustness of Multimodal RLVR](https://mlsanity.com/paper/2608.08802/) (2026)
- [FashionKG-RAG: Knowledge Graph-Enhanced Retrieval-Augmented Generation for Fashion Question Answering](https://mlsanity.com/paper/2608.22688/) (2026)
- [OmniPhys: A Unified Multimodal Benchmark for Physics Understanding and Generation from Chinese Educational Corpora](https://mlsanity.com/paper/2608.25398/) (2026)
- [ActICL: Post-Training for Agentic Multimodal In-Context Learning](https://mlsanity.com/paper/2610.19475/) (2026)

## Abstract (arXiv)

Multimodal reasoning, which integrates language and visual cues into problem solving and decision making, is a fundamental aspect of human intelligence and a crucial step toward artificial general intelligence. However, the evaluation of multimodal reasoning capabilities in Multimodal Large Language Models (MLLMs) remains inadequate. Most existing reasoning benchmarks are constrained by limited data size, narrow domain coverage, and unstructured knowledge distribution. To close these gaps, we introduce MDK12-Bench, a multi-disciplinary benchmark assessing the reasoning capabilities of MLLMs via real-world K-12 examinations. Spanning six disciplines (math, physics, chemistry, biology, geography, and information science), our benchmark comprises 140K reasoning instances across diverse difficulty levels from primary school to 12th grade. It features 6,827 instance-level knowledge point annotations based on a well-organized knowledge structure, detailed answer explanations, difficulty labels and cross-year partitions, providing a robust platform for comprehensive evaluation. Additionally, we present a novel dynamic evaluation framework to mitigate data contamination issues by bootstrapping question forms, question types, and image styles during evaluation. Extensive experiment on MDK12-Bench reveals the significant limitation of current MLLMs in multimodal reasoning. The findings on our benchmark provide insights into the development of the next-generation models. Our data and codes are available at https://github.com/LanceZPF/MDK12.