English

LongChart VQA: A Comprehensive Benchmark for MLLMs with Complex Multi-Chart Reasoning

Computation and Language 2026-08-02 v1 Artificial Intelligence Computer Vision and Pattern Recognition

Abstract

Multimodal large language models (MLLMs) are rapidly evolving with expanded context windows and stronger reasoning capabilities, enabling multi-chart understanding and multi-step inference. These abilities are increasingly important as MLLMs are adopted in complex agentic tasks. However, existing benchmarks largely emphasize single-chart perception, while simple chart-to-chart connections are insufficient to evaluate these capabilities. To capture multi-chart complexity while ensuring consistency and validity, we design a synthesis pipeline supported by latent graphs. Building on this pipeline, we introduce LongChart, a benchmark whose VQA sets contain an average of 6.5 images and 31.2 questions. We evaluate 10 state-of-the-art MLLMs and examine three factors that influence performance: reasoning patterns, auxiliary tools, and robustness to image perturbations. Our results show that MLLM accuracy decreases and varies substantially as computational complexity increases, highlighting directions for future research in multi-chart reasoning.

Cite

@article{arxiv.2608.01328,
  title  = {LongChart VQA: A Comprehensive Benchmark for MLLMs with Complex Multi-Chart Reasoning},
  author = {Ziyan Xiao and Yinghao Zhu and Wenting Zhang and Heaju Kim and Lequan Yu},
  journal= {arXiv preprint arXiv:2608.01328},
  year   = {2026}
}