2026 · Preprint
IChart2Code: Benchmarking Multimodal Large Language Models for Interactive Chart Code Generation
Benchmarks reconstruction of interactive charts from a reference screenshot, local data and specified actions. Its TRAIL framework uses Developer and Inspector agents with browser interaction traces to diagnose errors and revise the HTML/JavaScript implementation.
Scope and limitations
Covers 377 single-file HTML/JavaScript tasks with supplied data and explicit interaction requirements. Four models are evaluated with at most one repair round. Failing the Executability gate gives zero on scored dimensions; other rubric judgments use an MLLM, with human validation on 200 Direct outputs from 100 tasks and two models. Finite interactions and judge agreement do not establish complete application equivalence or recovery of hidden data and unspecified behavior.
Why it fits this collection
Adds an execution-aware benchmark for reproducing visual charts and their specified interactive state changes.
Publication and review details
- Venue
- arXiv
- Status
- Preprint
- Publication / posting date
- September 26, 2026
- Date source
- First arXiv v1 submission; no formal venue publication was verified.
- First arXiv submission
- September 26, 2026
- arXiv
- 2609.32413
- Reviewed arXiv version
- v1
- DOI
- 10.48550/arxiv.2609.32413
The six-author v1 identity matches arXiv and DataCite, which registered the arXiv DOI on 2026-09-29. The article uses the arXiv non-exclusive license. No author-linked public implementation, dataset release or corresponding license was verified in the reviewed full text and focused search. Referenced chart libraries and browser tools are not the benchmark release. No chart implementation, browser task, dataset payload or model was downloaded or executed.
Sources reviewed
Source review only; experiments were not rerun for this collection. Cite the original authors using the linked paper or BibTeX.