# ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

arXiv: https://arxiv.org/abs/2505.13444 · HTML: https://mlsanity.com/paper/2505.13444/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal reasoning, one of 17 directions in LLM reasoning.
- Builds on 12 of its 45 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM reasoning / [Multimodal reasoning](https://mlsanity.com/lr/multimodal-reasoning/)
- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 12 of 12)

- [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-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code](https://mlsanity.com/paper/2403.07974/) (2024)
- [Humanity's Last Exam](https://mlsanity.com/paper/2501.14249/) (2025)
- [FigureQA: An Annotated Figure Dataset for Visual Reasoning](https://mlsanity.com/paper/1710.07300/) (2017)
- [ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning](https://mlsanity.com/paper/2402.12185/) (2024)
- [ChartBench: A Benchmark for Complex Visual Reasoning in Charts](https://mlsanity.com/paper/2312.15915/) (2023)
- [CodeElo: Benchmarking Competition-level Code Generation of LLMs with Human-comparable Elo Ratings](https://mlsanity.com/paper/2501.01257/) (2025)
- [ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering](https://mlsanity.com/paper/2504.05506/) (2025)
- [Distill Visual Chart Reasoning Ability from LLMs to MLLMs](https://mlsanity.com/paper/2410.18798/) (2024)

## Built on by (most cited first, 30 of 32)

- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers](https://mlsanity.com/paper/2506.23918/) (2025)
- [Chart-R1: Chain-of-Thought Supervision and Reinforcement for Advanced Chart Reasoner](https://mlsanity.com/paper/2507.15509/) (2025)
- [MMDeepResearch-Bench: A Benchmark for Multimodal Deep Research Agents](https://mlsanity.com/paper/2601.12346/) (2026)
- [ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch](https://mlsanity.com/paper/2601.13606/) (2026)
- [Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation](https://mlsanity.com/paper/2510.20812/) (2025)
- [SO-Bench: A Structural Output Evaluation of Multimodal LLMs](https://mlsanity.com/paper/2511.21750/) (2025)
- [ChartHal: A Fine-grained Framework Evaluating Hallucination of Large Vision Language Models in Chart Understanding](https://mlsanity.com/paper/2509.17481/) (2025)
- [When Models Judge Themselves: Unsupervised Self-Evolution for Multimodal Reasoning](https://mlsanity.com/paper/2603.21289/) (2026)
- [Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results](https://mlsanity.com/paper/2604.21965/) (2026)
- [Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation](https://mlsanity.com/paper/2607.23125/) (2026)
- [Composition-Grounded Data Synthesis for Visual Reasoning](https://mlsanity.com/paper/2510.15040/) (2025)
- [See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning](https://mlsanity.com/paper/2512.22120/) (2025)
- [MERRIN: A Benchmark for Multimodal Evidence Retrieval and Reasoning in Noisy Web Environments](https://mlsanity.com/paper/2604.13418/) (2026)
- [ChartREG++: Towards Benchmarking and Improving Chart Referring Expression Grounding under Diverse referring clues and Multi-Target Referring](https://mlsanity.com/paper/2605.07415/) (2026)
- [FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions](https://mlsanity.com/paper/2509.17177/) (2025)
- [Enginuity: A Dataset and Benchmark for Vision-Language Understanding of Engineering Diagrams](https://mlsanity.com/paper/2606.03410/) (2026)
- [VisualFLIP: Do Predictions Depend on Task-Critical Visual Evidence in Multimodal Reasoning?](https://mlsanity.com/paper/2606.07872/) (2026)
- [LongChart VQA: A Comprehensive Benchmark for MLLMs with Complex Multi-Chart Reasoning](https://mlsanity.com/paper/2608.01328/) (2026)
- [TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models](https://mlsanity.com/paper/2608.28701/) (2026)
- [DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents](https://mlsanity.com/paper/2609.02059/) (2026)
- [A Vision for Multisensory Intelligence: Sensing, Science, and Synergy](https://mlsanity.com/paper/2601.04563/) (2026)
- [Toward a Machine Bertin: Why Visualization Needs Design Principles for Machine Cognition](https://mlsanity.com/paper/2602.01527/) (2026)
- [Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models](https://mlsanity.com/paper/2604.03157/) (2026)
- [Multimodal QUD: Inquisitive Questions from Scientific Figures](https://mlsanity.com/paper/2604.23733/) (2026)
- [CURV: Enhancing Chart Understanding Through Curriculum Visual Grounded Reasoning](https://mlsanity.com/paper/2608.02833/) (2026)
- [Chartography: A Benchmark for Professional Chart Understanding](https://mlsanity.com/paper/2608.10677/) (2026)
- [LegendBench: A Diagnostic Benchmark for Legend Understanding with Counterfactual Interventions](https://mlsanity.com/paper/2609.24172/) (2026)
- [Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation Enforcement](https://mlsanity.com/paper/2609.24243/) (2026)
- [Multimodal Thinking with Renderable Programs](https://mlsanity.com/paper/2609.30130/) (2026)

## Abstract (arXiv)

Chart understanding presents a unique challenge for large vision-language models (LVLMs), as it requires the integration of sophisticated textual and visual reasoning capabilities. However, current LVLMs exhibit a notable imbalance between these skills, falling short on visual reasoning that is difficult to perform in text. We conduct a case study using a synthetic dataset solvable only through visual reasoning and show that model performance degrades significantly with increasing visual complexity, while human performance remains robust. We then introduce ChartMuseum, a new Chart Question Answering (QA) benchmark containing 1,162 expert-annotated questions spanning multiple reasoning types, curated from real-world charts across 184 sources, specifically built to evaluate complex visual and textual reasoning. Unlike prior chart understanding benchmarks -- where frontier models perform similarly and near saturation -- our benchmark exposes a substantial gap between model and human performance, while effectively differentiating model capabilities: although humans achieve 93% accuracy, the best-performing model Gemini-2.5-Pro attains only 63.0%, and the leading open-source LVLM Qwen2.5-VL-72B-Instruct achieves only 38.5%. Moreover, on questions requiring primarily visual reasoning, all models experience a 35%-55% performance drop from text-reasoning-heavy question performance. Lastly, our qualitative error analysis reveals specific categories of visual reasoning that are challenging for current LVLMs.