PulseAugur
EN
LIVE 07:10:34

New benchmark SciFigure2Code tests AI's ability to generate code from scientific figures

By PulseAugur Editorial · [1 sources] ·

A new benchmark called SciFigure2Code has been introduced to evaluate AI's ability to reconstruct scientific figures into editable code. The benchmark focuses on recovering the hidden provenance of figures, such as the data and plotting code, from their visual representation. Role-specialized Codex agents were used to generate and refine Python programs that capture the arrangement, hierarchy, encodings, and typography of scientific panels. While current zero-shot models show weak performance in execution and structural fidelity, Claude Opus 4.7 and Claude Opus 4.6 demonstrated leading capabilities in image-only and caption-assisted reconstruction, respectively. AI

IMPACT This benchmark could drive improvements in AI's ability to interpret and reproduce scientific visualizations, potentially accelerating research reproducibility.

RANK_REASON The item describes a new benchmark and associated research paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New benchmark SciFigure2Code tests AI's ability to generate code from scientific figures

How we ranked this

Signal score
34 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The item describes a new benchmark and associated research paper published on arXiv. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CV TIER_1 English(EN) · Wentao Li, Yibo Wu, Yizhe Chen, Ruixuan Chen, Jiangjie Qiu, Yijun Li, Zhao Leyi, Xiaonan Wang ·

    SciFigure2Code: An AI-Reconstructed Benchmark for Scientific Figure-to-Code

    arXiv:2609.08155v2 Announce Type: replace Abstract: Scientific figures are the interface through which research claims are inspected and reused, but final published panels rarely expose the data or plotting code that produced them. Recovering this hidden provenance from pixels is…

RELATED ENTITIES

RELATED TOPICS