Cookie-Bench - HTML Dynamic: leaderboard

Cookie-Bench (2026) tests LLMs on front-end web development over 1,000 queries in 11 domains, with an autonomous evaluator that operates each generated page and scores the recorded session for functionality and aesthetics against human-calibrated rubrics, on a 0 to 100 scale. This board covers the interactive-application queries in HTML mode, one self-contained file written directly from the query; higher is better.

Metric: Cookie total score (0-100) from the autonomous Cookie evaluator, which drives the rendered page and judges the continuous execution video against human-calibrated functionality and aesthetics rubrics, on the dynamic (interactive-application) queries, HTML mode: the model receives only the query and returns one self-contained HTML file, with no scaffold or tools; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 13 models tracked. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Claude Opus 4.783.5#85
2Kimi K2.680.8#192
3Claude Opus 4.679#113
4GPT-5.476.9#135
5DeepSeek V4 Pro76.8#196
6GLM-5.176.5#198
7Qwen 3.6 Plus74.3#238
8MiMo-V2-Pro73.8#353
9Gemini 3.1 Pro (Preview)73.7#99
10DeepSeek V4 Flash72.4#267
11Qwen 3.6 27B69.6#351
12Gemini 3 Flash65.5#175
13Qwen 3.6 35B A3B61.7#481

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=cookie-bench-html-dynamic · How It Works · Data refreshed daily, snapshot 2026-11-21.