Back to browse
Millions of websites crawled for LLMs to rebuild the pricing pages

Millions of websites crawled for LLMs to rebuild the pricing pages

by kilroy123·Apr 12, 2026·3 points·1 comment

AI Analysis

●●SolidRabbit HoleBig BrainEye Candy

Massive LLM benchmark testing layout reconstruction on millions of real pricing pages.

Strengths
  • Massive scale dataset with millions of crawled pricing pages for evaluation.
  • Side-by-side comparison of 50 models on a consistent visual task.
Weaknesses
  • Limited practical utility beyond benchmarking and design inspiration.
  • Static snapshot of pricing pages may become outdated quickly.
Category
Target Audience

AI researchers, designers looking for pricing inspiration, LLM benchmarkers

Similar To

LMSYS Chatbot Arena · Mobbin · Pageflows

Post Description

I did a dumb thing by crawling millions of pages to find all the pricing pages I could.

Then I fed all of them to ~50 LLMs to see how good or bad they all did. Then I dumped it all on a page. Just because.

Here's a post on how I did this: https://pricepage.lol/how-i-built-pricepage-lol

Similar Projects

Design●●Solid

Design Memory – Extract design systems from live websites via CLI

Playwright-driven crawling + deterministic token extraction plus an LLM for semantic labeling is a clever pipeline — it doesn’t just scrape CSS, it produces an AI-optimized .design-memory folder with tokens, component recipes, and multi-page merge/diff capabilities. Expect variable fidelity on highly dynamic or framework-heavy sites since the approach depends on selector heuristics and an API key, but the CLI commands (learn, install, diff) and docs show this is more than a research sketch.

WizardryNiche Gem
saleban1031
103mo ago