← Back to stats

Case study: build a SaaS landing site

Same prompt, one shot, no hand-holding: "build a complete, production-quality SaaS landing site." Sent to 15 different models through codelazr, each to its own fresh repo, each deployed for real. No cherry-picking - every attempt is shown below, including the ones that didn't work.

The exact prompt used

Select all, copy, paste it yourself - same instruction, word for word.

Build a single-page SaaS landing site using Next.js (App Router), TypeScript, and Tailwind CSS. It should feel like a premium startup site (Linear, Vercel, Stripe) - not a generic template.

## Design
Dark mode, near-black background (#080808), white text, electric lime + cyan + purple accents, soft glows. Glassmorphism cards, soft borders, subtle glow effects, rounded-xl/2xl corners. Tasteful hover/fade motion - alive but not distracting. Fully responsive, semantic HTML.

## Single page (/) - all in one file plus a few components
- Sticky navbar (logo, nav links, Sign In, Get Started CTA)
- Hero: bold gradient headline, subheading, primary + secondary CTA
- Feature grid (6 features)
- 3 testimonials with names/avatars/companies
- Pricing section (3 tiers: Free/Pro/Team, cards only, no separate page)
- FAQ (4-5 questions)
- Final CTA + footer

## Components
Build 4-5 small reusable components (Navbar, Footer, GlassCard, PricingCard or similar) - not one giant file, but keep it tight.

## Copy
Real, compelling SaaS marketing copy - no lorem ipsum.

## Goal
Should look and feel like it could launch on Product Hunt today - polished and visually impressive, built efficiently in one focused page rather than a full multi-page site.
tencent/hy3:free result

tencent/hy3:free

$0.0004.1mVisit site →
poolside/laguna-m.1:free result

poolside/laguna-m.1:free

$0.0004.1mVisit site →
cohere/north-mini-code:free result

cohere/north-mini-code:free

$0.0002.0mVisit site →

Fast, reliable at bug-fix/build-error tasks in our testing.

poolside/laguna-xs-2.1:free result

poolside/laguna-xs-2.1:free

$0.0002.0mVisit site →
nvidia/nemotron-nano-9b-v2:free result

nvidia/nemotron-nano-9b-v2:free

$0.0004.6mVisit site →
openai/gpt-oss-120b result

openai/gpt-oss-120b

$0.00331sVisit site →
deepseek/deepseek-v4-flash result

deepseek/deepseek-v4-flash

$0.0103.5mVisit site →
xiaomi/mimo-v2.5 result

xiaomi/mimo-v2.5

$0.0262.3mVisit site →
google/gemini-3-flash-preview result

google/gemini-3-flash-preview

$0.03447sVisit site →
stepfun/step-3.7-flash result

stepfun/step-3.7-flash

$0.0412.5mVisit site →
deepseek/deepseek-v4-pro result

deepseek/deepseek-v4-pro

$0.1004.2mVisit site →
google/gemini-2.5-flash result

google/gemini-2.5-flash

$0.1213.4mVisit site →

Build had an error, fixed to deploy.

minimax/minimax-m3 result

minimax/minimax-m3

$0.1624.0mVisit site →
z-ai/glm-5.2 result

z-ai/glm-5.2

$0.4089.4mVisit site →

Didn't complete this round

google/gemini-2.5-flashNo package.json in edits - not a deployable project

Mostly hit our task time limit on a build this large - a real, known constraint, not hidden here.

Every repo and live deployment is real and public. Nothing here is staged.

Full testing history and methodology: /stats.