# Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

arXiv: https://arxiv.org/abs/2604.04192 · HTML: https://mlsanity.com/paper/2604.04192/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Builds on (most cited first, 7 of 7)

- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design](https://mlsanity.com/paper/2311.16974/) (2023)
- [CreatiPoster: Towards Editable and Controllable Multi-Layer Graphic Design Generation](https://mlsanity.com/paper/2506.10890/) (2025)
- [From Elements to Design: A Layered Approach for Automatic Graphic Design Composition](https://mlsanity.com/paper/2412.19712/) (2024)
- [Rethinking Layered Graphic Design Generation with a Top-Down Approach](https://mlsanity.com/paper/2507.05601/) (2025)
- [IGD: Instructional Graphic Design with Multimodal Layer Generation](https://mlsanity.com/paper/2507.09910/) (2025)
- [LICA: Layered Image Composition Annotations for Graphic Design Research](https://mlsanity.com/paper/2603.16098/) (2026)

## Built on by (most cited first, 8 of 8)

- [Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis](https://mlsanity.com/paper/2604.08809/) (2026)
- [DrawAI: Agentic Benchmark and Workflow for Making Raster Images Editable](https://mlsanity.com/paper/2608.00548/) (2026)
- [Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation](https://mlsanity.com/paper/2609.04298/) (2026)
- [Evaluating Design Video Generation: Metrics for Compositional Fidelity](https://mlsanity.com/paper/2605.16223/) (2026)
- [TASTE: A Designer-Annotated Multi-Dimensional Preference Dataset for AI-Generated Graphic Design](https://mlsanity.com/paper/2605.20731/) (2026)
- [GDB-Reward: From Evaluation Metrics to Training Rewards for Graphic Design](https://mlsanity.com/paper/2609.02813/) (2026)
- [AesCode: Aesthetic Code Generation with Decoupled Cross-Modal Rewards](https://mlsanity.com/paper/2610.18860/) (2026)
- [PLAYGROUND: Progressive Layout Generation with Render-Grounded Planning](https://mlsanity.com/paper/2610.18865/) (2026)

## Abstract (arXiv)

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 standardized metric taxonomy covering spatial accuracy, perceptual quality, text fidelity, semantic alignment, and structural validity. Our results reveal that current models fall short on the core challenges of professional design: spatial reasoning over complex layouts, faithful vector code generation, fine-grained typographic perception, and temporal decomposition of animations remain largely unsolved. While high-level semantic understanding is within reach, the gap widens sharply as tasks demand precision, structure, and compositional awareness. GDB provides a rigorous, reproducible testbed for tracking progress toward AI systems that can function as capable design collaborators. The full evaluation framework is publicly available.