Pith. sign in

REVIEW 12 cited by

Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.03163 v3 pith:ZW6XBW56 submitted 2024-03-05 cs.CL cs.CVcs.CY

Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End Engineering

classification cs.CL cs.CVcs.CY
keywords multimodalcodemetricsmodelswebpagesautomaticbenchmarkdesign2code
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Generative AI has made rapid advancements in recent years, achieving unprecedented capabilities in multimodal understanding and code generation. This can enable a new paradigm of front-end development in which multimodal large language models (MLLMs) directly convert visual designs into code implementations. In this work, we construct Design2Code - the first real-world benchmark for this task. Specifically, we manually curate 484 diverse real-world webpages as test cases and develop a set of automatic evaluation metrics to assess how well current multimodal LLMs can generate the code implementations that directly render into the given reference webpages, given the screenshots as input. We also complement automatic metrics with comprehensive human evaluations to validate the performance ranking. To rigorously benchmark MLLMs, we test various multimodal prompting methods on frontier models such as GPT-4o, GPT-4V, Gemini, and Claude. Our fine-grained break-down metrics indicate that models mostly lag in recalling visual elements from the input webpages and generating correct layout designs.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents

    cs.SE 2026-05 unverdicted novelty 7.0

    VISTA is a new benchmark for end-to-end visual spec-to-web-app generation by LLM agents, featuring five prompt conditions, manual UI annotations, multi-metric evaluation, and results on four agent systems showing part...

  2. From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements

    cs.SE 2026-05 unverdicted novelty 7.0

    TDDev automates the full TDD loop for web app generation from requirements, delivering 34-48 percentage point quality gains and zero manual intervention in user studies.

  3. UIPress: Bringing Optical Token Compression to UI-to-Code Generation

    cs.CL 2026-04 unverdicted novelty 7.0

    UIPress is the first encoder-side learned optical compression method for UI-to-Code that compresses visual tokens to 256, outperforming the uncompressed baseline by 7.5% CLIP score and the best inference-time baseline...

  4. Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

    cs.CV 2024-06 unverdicted novelty 7.0

    Cambrian-1 is a vision-centric multimodal LLM family that evaluates over 20 vision encoders, introduces CV-Bench and the Spatial Vision Aggregator, and releases open models, code, and data achieving strong performance...

  5. Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual Artifacts

    cs.AI 2026-06 unverdicted novelty 6.0

    Visual-SDPO distills visual feedback from rendered code outputs into a student policy via grounded credit weighting and GRPO, yielding over 10-point gains on chart/UI/slide benchmarks.

  6. ProductWebGen: Benchmarking Multimodal Product Webpage Generation

    cs.CV 2026-05 unverdicted novelty 6.0

    Introduces ProductWebGen benchmark for multimodal product webpage generation, compares editing-based vs unified-model workflows on 500 samples, and releases ProductWebGen-1k SFT dataset.

  7. UIBenchKit: A unified toolkit for design-to-code model evaluation

    cs.SE 2026-05 accept novelty 6.0

    UIBenchKit is a unified open-source toolkit providing plug-and-play evaluation for design-to-code generation models with consistent settings and multi-metric analysis.

  8. OpenGame: Open Agentic Coding for Games

    cs.SE 2026-04 unverdicted novelty 6.0

    OpenGame is the first open-source agentic framework for end-to-end web game creation, using Game Skills and GameCoder-27B to achieve state-of-the-art results on 150 prompts via a new benchmark measuring build health, ...

  9. MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

    cs.CV 2024-12 unverdicted novelty 6.0

    VPiT enables pretrained LLMs to perform both visual understanding and generation by predicting discrete text tokens and continuous visual tokens, with understanding data proving more effective than generation-specific data.

  10. I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications

    cs.CL 2026-05 unverdicted novelty 5.0

    A Paper-to-Interactive-System Agent and I-WebGenBench benchmark with 19 papers enable converting scientific PDFs into executable interactive web systems, with PaperVoyager framework shown to improve quality.

  11. HTMLCure: Turning Browser Experience into State Guided Repair for Interactive HTML

    cs.SE 2026-05 unverdicted novelty 5.0

    HTMLCure uses browser-executed interaction trajectories to diagnose and repair LLM HTML outputs, expanding 97K prompts into a 40K refined SFT set that lifts a 27B model to 50.6 on HTMLBench-400 and 81.2 on MiniAppBench.

  12. InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

    cs.CV 2024-07 conditional novelty 5.0

    InternLM-XComposer-2.5 is a 7B vision-language model supporting up to 96K context that reaches GPT-4V-level performance on image, video, and multi-turn tasks and adds LoRA-driven text-image composition capabilities.