From Charts to Code: A Hierarchical Benchmark for Multimodal Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910141239001088 |
|---|---|
| author | Tang, Jiahao Zhao, Henry Hengyuan Wu, Lijian Zhang, Zijian Tao, Yifei Mao, Dongxing Wan, Yang Tan, Jingru Zeng, Min Li, Min Wang, Alex Jinpeng |
| author_facet | Tang, Jiahao Zhao, Henry Hengyuan Wu, Lijian Zhang, Zijian Tao, Yifei Mao, Dongxing Wan, Yang Tan, Jingru Zeng, Min Li, Min Wang, Alex Jinpeng |
| contents | We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse real-world scenarios and progressively increasing task difficulty. It consists of three levels: Level 1 (Chart Reproduction) reproduces charts from a reference figure and user query; Level 2 (Chart Editing) involves complex modifications such as changing chart types or adding elements; and Level 3 (Long-Table to Chart Generation) requires models to transform long, information-dense tables into faithful charts following user instructions. To our knowledge, this is the first hierarchical benchmark that reflects practical chart2code usage while systematically scaling task complexity. In total, Chart2Code contains 2,023 tasks across 22 chart types, paired with multi-level evaluation metrics that assess both code correctness and the visual fidelity of rendered charts. We benchmark 25 state-of-the-art (SoTA) LMMs, including both proprietary and the latest open-source models such as GPT-5, Qwen2.5-VL, InternVL3/3.5, MiMo-VL, and Seed-1.6-VL. Experimental results demonstrate that even the SoTA model GPT-5 averages only 0.57 on code-based evaluation and 0.22 on chart-quality assessment across the editing tasks, underscoring the difficulty of Chart2Code. We anticipate this benchmark will drive advances in multimodal reasoning and foster the development of more robust and general-purpose LMMs. Our code and data are available on Chart2Code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_17932 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Charts to Code: A Hierarchical Benchmark for Multimodal Models Tang, Jiahao Zhao, Henry Hengyuan Wu, Lijian Zhang, Zijian Tao, Yifei Mao, Dongxing Wan, Yang Tan, Jingru Zeng, Min Li, Min Wang, Alex Jinpeng Software Engineering Artificial Intelligence We introduce Chart2Code, a new benchmark for evaluating the chart understanding and code generation capabilities of large multimodal models (LMMs). Chart2Code is explicitly designed from a user-driven perspective, capturing diverse real-world scenarios and progressively increasing task difficulty. It consists of three levels: Level 1 (Chart Reproduction) reproduces charts from a reference figure and user query; Level 2 (Chart Editing) involves complex modifications such as changing chart types or adding elements; and Level 3 (Long-Table to Chart Generation) requires models to transform long, information-dense tables into faithful charts following user instructions. To our knowledge, this is the first hierarchical benchmark that reflects practical chart2code usage while systematically scaling task complexity. In total, Chart2Code contains 2,023 tasks across 22 chart types, paired with multi-level evaluation metrics that assess both code correctness and the visual fidelity of rendered charts. We benchmark 25 state-of-the-art (SoTA) LMMs, including both proprietary and the latest open-source models such as GPT-5, Qwen2.5-VL, InternVL3/3.5, MiMo-VL, and Seed-1.6-VL. Experimental results demonstrate that even the SoTA model GPT-5 averages only 0.57 on code-based evaluation and 0.22 on chart-quality assessment across the editing tasks, underscoring the difficulty of Chart2Code. We anticipate this benchmark will drive advances in multimodal reasoning and foster the development of more robust and general-purpose LMMs. Our code and data are available on Chart2Code. |
| title | From Charts to Code: A Hierarchical Benchmark for Multimodal Models |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2510.17932 |