Lune

ACL Findings2026

PlotGen-Bench: Evaluating VLMs on Generating Visualization Code from Diverse Plots across Multiple Libraries

Yi Zhao, Zhen Yang, Shuaiqi Duan, Wenmeng Yu, Zhe Su, Jibing Gong, Jie Tang

Abstract

Recent advances in vision-language models (VLMs) have expanded their multimodal code generation capabilities, yet their ability to generate executable visualization code from plots, especially for complex 3D, animated, plot-toplot transformations, or multi-library scenarios, remains underexplored. To address this gap, we introduce PlotGen-Bench, a comprehensive benchmark for evaluating plot-to-code generation under realistic and complex visualization scenarios. The benchmark spans 9 major categories, 30 subcategories, and 3 core tasks-plot replication, plot transformation, and multi-library generation, covering both 2D, 3D and animated plots across 5 widely used visualization libraries. Through systematic evaluation of state-of-the-art open-and closed-source VLMs, we find that open-source models still lag considerably behind in visual fidelity and semantic consistency, despite achieving comparable code executability. Moreover, all models exhibit substantial degradation on reasoning-intensive tasks such as chart type conversion and animation generation. PlotGen-Bench establishes a rigorous foundation for advancing research toward more capable and reliable VLMs for visualization authoring and code synthesis, with all data and code available at https://plotgen.github.io.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems cites Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering
  • ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing cites ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
  • ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing cites ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation
  • ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation cites ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart Editing
  • ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation cites MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming Problems
  • ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code Generation cites ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code Generation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on7

  1. Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question AnsweringPan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu et al.NeurIPS 2022 · 2,727 citations
  2. ChartCoder: Advancing Multimodal Large Language Model for Chart-to-Code GenerationXuanle Zhao, Xianzhen Luo, Qi Shi, Chi Chen et al.ACL 2025 · 62 citations
  3. MMCode: Benchmarking Multimodal Large Language Models for Code Generation with Visually Rich Programming ProblemsKaixin Li, Yuchen Tian, Qisheng Hu, Ziyang Luo et al.EMNLP Findings 2024 · 8 citations
  4. ChartMimic: Evaluating LMM's Cross-Modal Reasoning Capability via Chart-to-Code GenerationCheng Yang, Chufan Shi, Yaxin Liu, Bo Shui et al.ICLR 2025 · 3 citations
  5. ChartEdit: How Far Are MLLMs From Automating Chart Analysis? Evaluating MLLMs' Capability via Chart EditingXuanle Zhao, Xuexin Liu, Haoyue Yang, Xianzhen Luo et al.ACL Findings 2025 · 1 citation

Related papers

  1. RealChart2Code: Bridging the Gap in Real-World Chart-to-Code Generation via Multi-Task EvaluationJiajun Zhang, Yuying Li, Zhixun Li, Xingyu Guo et al.ACL 2026
  2. PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data VisualizationJiajun Zhang, Jianke Zhang, Zeyu Cui, Jiaxi Yang et al.ICML 2026
  3. Dashboard2Code: Evaluating Multimodal Models on Reconstructing Interactive DashboardsTianhao Niu, Ziyu Han, Qiguang Chen, Shiqi Zhou et al.ACL 2026
  4. From Charts to Code: A Hierarchical Benchmark for Multimodal ModelsJiahao Tang, Henry Hengyuan Zhao, Lijian Wu, Zijian Zhang et al.ACL 2026 · 5 citations
  5. VisCoder2: Building Multi-Language Visualization Coding AgentsYuansheng Ni, Songcheng Cai, Xiangchao Chen, Jiarong Liang et al.ICLR 2026 · 3 citations
Dusk over the sea between two cliffs drawn in fine vertical lines