ChartE$^{3}$: A Comprehensive Benchmark for End-to-End Chart Editing

TL;DR

ChartE$^{3}$ introduces a comprehensive benchmark for evaluating end-to-end chart editing models, emphasizing both local and global edits without intermediate representations, revealing significant gaps in current model capabilities.

Contribution

The paper presents the first large-scale, high-quality benchmark for end-to-end chart editing that evaluates models directly on visual and code-based chart modifications.

Findings

State-of-the-art models perform poorly on global editing tasks.

Benchmark contains over 1,200 curated samples with multimodal instructions.

Current models show significant limitations in holistic chart transformations.

Abstract

Charts are a fundamental visualization format for structured data analysis. Enabling end-to-end chart editing according to user intent is of great practical value, yet remains challenging due to the need for both fine-grained control and global structural consistency. Most existing approaches adopt pipeline-based designs, where natural language or code serves as an intermediate representation, limiting their ability to faithfully execute complex edits. We introduce ChartE$^{3}$, an End-to-End Chart Editing benchmark that directly evaluates models without relying on intermediate natural language programs or code-level supervision. ChartE$^{3}$ focuses on two complementary editing dimensions: local editing, which involves fine-grained appearance changes such as font or color adjustments, and global editing, which requires holistic, data-centric transformations including data filtering and trend line addition. ChartE$^{3}$ contains over 1,200 high-quality samples constructed via a well-designed data pipeline with human curation. Each sample is provided as a triplet of a chart image, its underlying code, and a multimodal editing instruction, enabling evaluation from both objective and subjective perspectives. Extensive benchmarking of state-of-the-art multimodal large language models reveals substantial performance gaps, particularly on global editing tasks, highlighting critical limitations in current end-to-end chart editing capabilities.