# Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation Source: [Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation]() Collection index: [llms.txt]() Data updated: 2026-06-02T05:02:08.515Z Authors: Haoyue Yang, Zhangxiao Shen, Fan Ding, Hangting Lou, Yifeng Kou, Haoqing Yu, Jingyao Li, Zhengfan Wu, Siqi Bao, Jing Liu, Hua Wu Published: 2026-05-28T14:30:33.000Z ## Abstract Front-end web code has become a core product surface for every frontier LLM release, yet evaluating these interactive applications at development speed remains costly because human-judged leaderboards like Arena do not scale. Existing automated proxies typically lean on reference implementations, test suites, or rigid checklists, and tend to miss the reasoned synthesis a human reviewer performs over a live session. We articulate a new evaluation regime that is simultaneously reference-free, autonomously driven, and holistically reasoned, and instantiate it through two artifacts. \\textbf{\\dataname} is an 11-domain, 54-leaf, 1,000-query WebDev benchmark spanning both static-presentation and interactive-application tasks, balanced across three difficulty tiers and three target-language groups, with briefs rewritten to resist recall from circulated prompts. \\textbf{\\framename}, grounded in Flavell's metacognitive monitoring, separates evidence accumulation from judgment across three stages: Static Perception forms a first impression from passive observation; Agent-Driven Interaction explores the application autonomously while capturing continuous screen video, audio, and per-step screenshots; Dynamic Scoring issues holistic functionality and aesthetics verdicts with structured failure attribution only after the evidence chain is complete. On \\dataname, \\framename aligns closely with expert human ratings while surfacing substantial headroom across 13 frontier LLMs on interactive web generation. \\noindenthttps://anonymous.4open.science/r/Cookie-3CE/ ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [React UI Generation on Cookie-Bench (Dynamic split)](): React UI Generation; Cookie-Bench (Dynamic split); Functionality Score: not recorded. - [React UI Generation on Cookie-Bench Overall](): React UI Generation; Cookie-Bench Overall; Total Score: not recorded. - [HTML UI Generation on Cookie-Bench Static split](): HTML UI Generation; Cookie-Bench Static split; Functionality Score: not recorded. - [React UI Generation on Cookie-Bench Static](): React UI Generation; Cookie-Bench Static; Functionality Score: not recorded. ## Original sources and implementation [Original paper]() [PDF]()