Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks
Adrienne Deganutti, Elad Hirsch, Haonan Zhu, Jaejung Seol, Purvanshi Mehta

TL;DR
GraphicDesignBench (GDB) is a comprehensive benchmark suite for evaluating AI models across various professional graphic design tasks, highlighting current limitations in spatial reasoning, vector graphics, and animation understanding.
Contribution
The paper introduces GDB, the first benchmark targeting the full spectrum of professional graphic design tasks, with standardized evaluation metrics and real-world design templates.
Findings
Current models struggle with complex layout reasoning
Models have difficulty generating accurate vector graphics
Semantic understanding is better than structural and spatial accuracy
Abstract
We introduce GraphicDesignBench (GDB), the first comprehensive benchmark suite designed specifically to evaluate AI models on the full breadth of professional graphic design tasks. Unlike existing benchmarks that focus on natural-image understanding or generic text-to-image synthesis, GDB targets the unique challenges of professional design work: translating communicative intent into structured layouts, rendering typographically faithful text, manipulating layered compositions, producing valid vector graphics, and reasoning about animation. The suite comprises 50 tasks organized along five axes: layout, typography, infographics, template & design semantics and animation, each evaluated under both understanding and generation settings, and grounded in real-world design templates drawn from the LICA layered-composition dataset. We evaluate a set of frontier closed-source models using a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
