# VLM@school -- Evaluation of AI image understanding on German middle school knowledge

arXiv: https://arxiv.org/abs/2506.11604 · HTML: https://mlsanity.com/paper/2506.11604/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 36 of its 49 references that are in the map.
- First posted on arXiv 13 Jun 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)

## Builds on (most cited first, 30 of 36)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning](https://mlsanity.com/paper/2203.10244/) (2022)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [A Diagram Is Worth A Dozen Images](https://mlsanity.com/paper/1603.07396/) (2016)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023)
- [LLaVA-CoT: Let Vision Language Models Reason Step-by-Step](https://mlsanity.com/paper/2411.10440/) (2024)
- [VLMEvalKit: An Open-Source Toolkit for Evaluating Large Multi-Modality Models](https://mlsanity.com/paper/2407.11691/) (2024)
- [Kimi-VL Technical Report](https://mlsanity.com/paper/2504.07491/) (2025)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [AI and the Everything in the Whole Wide World Benchmark](https://mlsanity.com/paper/2111.15366/) (2021)
- [Replacing Judges with Juries: Evaluating LLM Generations with a Panel of Diverse Models](https://mlsanity.com/paper/2404.18796/) (2024)
- [State of What Art? A Call for Multi-Prompt LLM Evaluation](https://mlsanity.com/paper/2401.00595/) (2023)
- [MoE-LLaVA: Mixture of Experts for Large Vision-Language Models](https://mlsanity.com/paper/2401.15947/) (2024)
- [Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging](https://mlsanity.com/paper/1909.12475/) (2019)
- [AI Sandbagging: Language Models can Strategically Underperform on Evaluations](https://mlsanity.com/paper/2406.07358/) (2024)
- [The Benchmark Lottery](https://mlsanity.com/paper/2107.07002/) (2021)
- [M3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning](https://mlsanity.com/paper/2306.04387/) (2023)
- [Is LLM-as-a-Judge Robust? Investigating Universal Adversarial Attacks on Zero-shot LLM Assessment](https://mlsanity.com/paper/2402.14016/) (2024)
- [BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices](https://mlsanity.com/paper/2411.12990/) (2024)
- [The Art of Saying No: Contextual Noncompliance in Language Models](https://mlsanity.com/paper/2407.12043/) (2024)
- [An Empirical Study of LLM-as-a-Judge for LLM Evaluation: Fine-tuned Judge Model is not a General Substitute for GPT-4](https://mlsanity.com/paper/2403.02839/) (2024)
- [xGQA: Cross-Lingual Visual Question Answering](https://mlsanity.com/paper/2109.06082/) (2021)
- [Can We Trust AI Benchmarks? An Interdisciplinary Review of Current Issues in AI Evaluation](https://mlsanity.com/paper/2502.06559/) (2025)
- [Q-VLM: Post-training Quantization for Large Vision-Language Models](https://mlsanity.com/paper/2410.08119/) (2024)
- [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, 2 of 2)

- [SITUATE -- Synthetic Object Counting Dataset for VLM training](https://mlsanity.com/paper/2602.00108/) (2026)
- [Unlocking UML Class Diagram Understanding in Vision Language Models](https://mlsanity.com/paper/2605.11634/) (2026)

## Abstract (arXiv)

This paper introduces a novel benchmark dataset designed to evaluate the capabilities of Vision Language Models (VLMs) on tasks that combine visual reasoning with subject-specific background knowledge in the German language. In contrast to widely used English-language benchmarks that often rely on artificially difficult or decontextualized problems, this dataset draws from real middle school curricula across nine domains including mathematics, history, biology, and religion. The benchmark includes over 2,000 open-ended questions grounded in 486 images, ensuring that models must integrate visual interpretation with factual reasoning rather than rely on superficial textual cues. We evaluate thirteen state-of-the-art open-weight VLMs across multiple dimensions, including domain-specific accuracy and performance on adversarial crafted questions. Our findings reveal that even the strongest models achieve less than 45% overall accuracy, with particularly poor performance in music, mathematics, and adversarial settings. Furthermore, the results indicate significant discrepancies between success on popular benchmarks and real-world multimodal understanding. We conclude that middle school-level tasks offer a meaningful and underutilized avenue for stress-testing VLMs, especially in non-English contexts. The dataset and evaluation protocol serve as a rigorous testbed to better understand and improve the visual and linguistic reasoning capabilities of future AI systems.