@inproceedings{sun-etal-2026-fullfront,
title = "{F}ull{F}ront: Benchmarking {MLLM}s Across the Full Front-End Engineering Workflow",
author = "Sun, Haoyu and
Wang, Huichen Will and
Gu, Jiawei and
Li, Linjie and
Cheng, Yu",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1358/",
pages = "30948--30994",
ISBN = "979-8-89176-459-0",
abstract = "We present \textbf{FullFront}, a workflow-grounded benchmark for Multimodal Large Language Models (MLLMs) across the front-end engineering pipeline{---}conceptualization, comprehension, and implementation{---}rather than evaluating any single stage in isolation. FullFront contributes along three axes: (i) a unified task formulation covering Webpage Design, Webpage Perception QA, and Webpage Code Generation (8 subtasks, 2{,}700 items); (ii) a controlled two-stage data construction pipeline that converts real-world webpages into standardized HTML with a 15-category copyright-safe image substitution scheme; and (iii) a reliability-oriented evaluation framework whose Code Score and Gemini Visual Score are validated against human judgment, cross-judge agreement, pipeline bias, and sensitivity stress tests. Across 12 MLLMs we observe a stable closed-source top tier, a Perception{--}Implementation Gap with distinct failure modes (Coding Bottleneck'' for open-source, Grounding Failure'' for proprietary), and heterogeneous open/closed capability profiles{---}patterns that isolated benchmarks cannot expose."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-fullfront">
<titleInfo>
<title>FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoyu</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huichen</namePart>
<namePart type="given">Will</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>We present FullFront, a workflow-grounded benchmark for Multimodal Large Language Models (MLLMs) across the front-end engineering pipeline—conceptualization, comprehension, and implementation—rather than evaluating any single stage in isolation. FullFront contributes along three axes: (i) a unified task formulation covering Webpage Design, Webpage Perception QA, and Webpage Code Generation (8 subtasks, 2,700 items); (ii) a controlled two-stage data construction pipeline that converts real-world webpages into standardized HTML with a 15-category copyright-safe image substitution scheme; and (iii) a reliability-oriented evaluation framework whose Code Score and Gemini Visual Score are validated against human judgment, cross-judge agreement, pipeline bias, and sensitivity stress tests. Across 12 MLLMs we observe a stable closed-source top tier, a Perception–Implementation Gap with distinct failure modes (Coding Bottleneck” for open-source, Grounding Failure” for proprietary), and heterogeneous open/closed capability profiles—patterns that isolated benchmarks cannot expose.</abstract>
<identifier type="citekey">sun-etal-2026-fullfront</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1358/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>30948</start>
<end>30994</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow
%A Sun, Haoyu
%A Wang, Huichen Will
%A Gu, Jiawei
%A Li, Linjie
%A Cheng, Yu
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F sun-etal-2026-fullfront
%X We present FullFront, a workflow-grounded benchmark for Multimodal Large Language Models (MLLMs) across the front-end engineering pipeline—conceptualization, comprehension, and implementation—rather than evaluating any single stage in isolation. FullFront contributes along three axes: (i) a unified task formulation covering Webpage Design, Webpage Perception QA, and Webpage Code Generation (8 subtasks, 2,700 items); (ii) a controlled two-stage data construction pipeline that converts real-world webpages into standardized HTML with a 15-category copyright-safe image substitution scheme; and (iii) a reliability-oriented evaluation framework whose Code Score and Gemini Visual Score are validated against human judgment, cross-judge agreement, pipeline bias, and sensitivity stress tests. Across 12 MLLMs we observe a stable closed-source top tier, a Perception–Implementation Gap with distinct failure modes (Coding Bottleneck” for open-source, Grounding Failure” for proprietary), and heterogeneous open/closed capability profiles—patterns that isolated benchmarks cannot expose.
%U https://aclanthology.org/2026.emnlp-main.1358/
%P 30948-30994
Markdown (Informal)
[FullFront: Benchmarking MLLMs Across the Full Front-End Engineering Workflow](https://aclanthology.org/2026.emnlp-main.1358/) (Sun et al., EMNLP 2026)
ACL