BENCHMARK 1 · SLOTKEEPER BOOKING APP · TESTED OCT 14–25, 2026 · ONE RUN PER TOOL How we test →

Home / Showcase

What each tool really built

Five AI app builders and ChatGPT's coding agent got the same prompt for a yoga studio's booking app. Here's what each one made, screen by screen, with live links and the receipt behind every score.

Read the prompt every tool got
Build a web app called "SlotKeeper" for a small service business to take bookings.

Public side (no login needed):
- A landing page showing the business name "Maple Yoga Studio" and a list of upcoming time slots (date, start time, duration, spots left).
- Clicking a slot opens a booking form: full name, email, phone (optional), notes (optional). Validate that name and a valid email are required.
- If a slot has spots left, booking it reduces spots by 1 and shows a confirmation page with the booking details.
- If a slot is full, the button says "Join waitlist" instead, and the same form adds the person to that slot's waitlist with their position number.
- The same email cannot book the same slot twice.

Owner side (login required):
- Email + password sign up and login for the owner. Only logged-in owners can see the admin area; logged-out visitors trying /admin are redirected to login.
- Admin dashboard: create, edit, and delete slots (date, start time, duration in minutes, capacity).
- For each slot, see the list of bookings and the waitlist. The owner can cancel a booking; when a booking is cancelled, the first person on the waitlist is automatically moved into the booking.
- A simple stats line at the top: total upcoming slots, total bookings, total waitlisted.

Requirements:
- Store all data in a real persistent database (data must survive a page refresh and a redeploy).
- Clean, modern, mobile-friendly design.
- Seed 3 example slots for the next 7 days, one of them with capacity 1.
- Deploy it to a public URL I can share.

On a phone

Live apps, captured Oct 25, 2026 on a phone-sized screen (412 px wide). Slot dates and spots left are today's, not the test day's.

On a laptop

The same live apps at 1280 × 800, captured Oct 25, 2026. The address bar shows each app's real address.

  • 1st94.75Bolt.new

    Bolt.new's live SlotKeeper home page on a laptop, headline "Find your breath. Book your mat."
  • 2nd93.5Base44

    Base44's live SlotKeeper home page on a laptop, headline "A calm hour, just for you."
  • 3rd90.875v0

    v0's live SlotKeeper home page on a laptop, headline "Find your still point."
  • 4th87.25Lovable

    Lovable's live SlotKeeper home page on a laptop, headline "Find your breath. Save your mat."
  • 5th83.625Replit Agent

    Replit Agent's live SlotKeeper home page on a laptop, headline "Find your own rhythm."
  • Baseline82.5ChatGPT Codex

    ChatGPT Codex's live SlotKeeper home page on a laptop, headline "Find your balance. Make time for you."

Booking confirmed

What a customer saw after a test booking. Captured from each app between Oct 21 and Oct 25, 2026, during or after its test. Emails are redacted or test-only.

Owner dashboard

The studio owner's view after logging in. Captured from each app between Oct 21 and Oct 25, 2026, during or after its test. Emails are redacted or test-only.

  • 1st94.75Bolt.new

    Bolt's owner dashboard with stat cards for 3 upcoming slots, 2 bookings and 1 waitlisted
  • 2nd93.5Base44

    Not shown: the only dashboard capture shows a personal email address and an empty board.

  • 3rd90.875v0

    Not captured: the owner credentials were lost in a machine restore, and sign-up was closed.

  • 4th87.25Lovable

    Lovable's owner dashboard listing slots and bookings, emails redacted
  • 5th83.625Replit Agent

    Replit's owner dashboard with stat cards for 3 classes, 2 booked places and 1 on the waitlist
  • Baseline82.5ChatGPT Codex

    Codex's owner dashboard, "A little room to grow.", with tiles for 3 upcoming sessions, 4 bookings and 1 on the waitlist

Head to head

Put any two apps next to each other: the phone home page, the booking confirmation and the owner view, then the points on each part of the rubric. It starts with the top specialist against ChatGPT's Codex.

Bolt.new

94.75 /100

1st

Bolt.new's live SlotKeeper home page on a phone, headline "Find your breath. Book your mat."
Bolt's confirmation: a green "You're booked!" card with the session date and time
Bolt's owner dashboard with stat cards for 3 upcoming slots, 2 bookings and 1 waitlisted

ChatGPT Codex

82.5 /100

Baseline

General-AI baseline, not ranked: a Plus-level plan, 2 fix prompts and a human-made hosting account. Bug score under review: 83.5 under our −1-per-minor rule.

ChatGPT Codex's live SlotKeeper home page on a phone, headline "Find your balance. Make time for you."
Codex's confirmation reading "You're on the mat." for Morning Flow, Monday, October 26, with the email redacted
Codex's owner dashboard, "A little room to grow.", with tiles for 3 upcoming sessions, 4 bookings and 1 on the waitlist
  • Works30 vs 30same
  • Time15 vs 9+6
  • Bugs11 vs 11same
  • Design13.75 vs 12.5+1.25
  • Deploy15 vs 10+5
  • Cost10 vs 10same
  • Total94.75 vs 82.5+12.25

Full score comparison for any pair

Try the live apps

These are the apps exactly as each tool published them. They hold test bookings only. Please don't enter real personal details.

Cursor, our reference run, never deployed: its free plan ran out first, so there's no app to show.

The receipts

Every score, with the prompt, the time, the human minutes and the points behind it. Swipe for all six.

  • BenchCoded LabTest receipt

    Bolt.new94.75 / 100

    Works
    30/30
    Time
    15/15
    Bugs
    11/15
    Design
    13.75/15
    Deploy
    15/15
    Cost
    10/10
    Prompts sent
    1 (no fix prompts)
    Time to working version
    ~7 min
    Human minutes
    Not recorded (protocol v1)
    Checks
    10/10
    Bugs
    1 major · 2 minor
    Plan
    Free · 1M-token survey bonus
    Cost
    $0
    More receipt fields
    Receipt ID
    BC-SK1-BOLT
    Status
    Published · TESTED
    Protocol
    v1: free plan, no baseline
    Tool
    Bolt.new
    Benchmark
    SlotKeeper booking app
    Date
    Oct 21, 2026
    Plan in full
    Free
    Model
    Not recorded
    Cost basis
    Usage $0 on the free plan (1M-token survey bonus on the account)
    Relationships
    None
    Retest due
    Dec 20, 2026
    Source: internal scorecard, recorded Oct 21, 2026. Full review
  • BenchCoded LabTest receipt

    Base4493.5 / 100

    Works
    30/30
    Time
    15/15
    Bugs
    11/15
    Design
    12.5/15
    Deploy
    15/15
    Cost
    10/10
    Prompts sent
    1 (no fix prompts)
    Time to working version
    8–9 min
    Human minutes
    Not recorded (protocol v1)
    Checks
    10/10
    Bugs
    4 minor
    Plan
    Free
    Cost
    Free plan (usage not shown)
    More receipt fields
    Receipt ID
    BC-SK1-BASE44
    Status
    Published · TESTED
    Protocol
    v1: free plan, no baseline
    Tool
    Base44
    Benchmark
    SlotKeeper booking app
    Date
    Oct 14–15, 2026
    Plan in full
    Free
    Model
    Not shown by Base44
    Cost basis
    Free plan; usage not shown by the tool
    Relationships
    None
    Retest due
    Dec 14, 2026
    Source: internal scorecard, recorded Oct 14–15, 2026. Full review
  • BenchCoded LabTest receipt

    v090.875 / 100

    Works
    30/30
    Time
    12/15
    Bugs
    12/15
    Design
    11.875/15
    Deploy
    15/15
    Cost
    10/10
    Prompts sent
    1 (no fix prompts)
    Time to working version
    ~20 min
    Human minutes
    Not recorded (protocol v1)
    Checks
    10/10
    Bugs
    3 minor
    Plan
    Free
    Cost
    $0
    More receipt fields
    Receipt ID
    BC-SK1-V0
    Status
    Published · TESTED
    Protocol
    v1: free plan, no baseline
    Tool
    v0
    Benchmark
    SlotKeeper booking app
    Date
    Oct 22, 2026
    Plan in full
    Free
    Model
    Not recorded
    Cost basis
    Usage $0 on the free plan
    Relationships
    None
    Retest due
    Dec 21, 2026
    Source: internal scorecard, recorded Oct 22, 2026. Full review
  • BenchCoded LabTest receipt

    Lovable87.25 / 100

    Works
    30/30
    Time
    12/15
    Bugs
    9/15
    Design
    11.25/15
    Deploy
    15/15
    Cost
    10/10
    Prompts sent
    1 (no fix prompts)
    Time to working version
    ~18 min active
    Human minutes
    Not recorded (protocol v1)
    Checks
    10/10
    Bugs
    1 critical · 2 minor
    Plan
    Free · waited overnight for credits
    Cost
    $0
    More receipt fields
    Receipt ID
    BC-SK1-LOVABLE
    Status
    Published · TESTED
    Protocol
    v1: free plan, no baseline
    Tool
    Lovable
    Benchmark
    SlotKeeper booking app
    Date
    Oct 21–22, 2026
    Plan in full
    Free
    Model
    Not recorded
    Cost basis
    Usage $0 on the free plan, after an overnight credit wait
    Relationships
    None
    Retest due
    Dec 21, 2026
    Under review: 86.25 if our 5-point critical-bug rule is applied (the scorecard took 4). Source: internal scorecard, recorded Oct 21–22, 2026. Full review
  • BenchCoded LabTest receipt

    Replit Agent83.625 / 100

    Works
    30/30
    Time
    8/15
    Bugs
    10/15
    Design
    10.625/15
    Deploy
    15/15
    Cost
    10/10
    Prompts sent
    1 (no fix prompts)
    Time to working version
    ~23 min to live
    Human minutes
    Not recorded (protocol v1)
    Checks
    10/10
    Bugs
    5 minor
    Plan
    Free · deploy lasts 29 days
    Cost
    $0
    More receipt fields
    Receipt ID
    BC-SK1-REPLIT
    Status
    Published · TESTED
    Protocol
    v1: free plan, no baseline
    Tool
    Replit Agent
    Benchmark
    SlotKeeper booking app
    Date
    Oct 24, 2026
    Plan in full
    Free
    Model
    Not recorded
    Cost basis
    Usage $0 on the free plan
    Relationships
    None
    Retest due
    Dec 23, 2026
    87.625 if time counts to the agent's 13-minute finish, which would rank it above Lovable (87.25, or 86.25 under review). Source: internal scorecard, recorded Oct 24, 2026. Full review
  • BenchCoded LabTest receipt

    ChatGPT Codex82.5 / 100

    Works
    30/30
    Time
    9/15
    Bugs
    11/15
    Design
    12.5/15
    Deploy
    10/15
    Cost
    10/10
    Prompts sent
    4: the prompt, 2 fixes, 1 deploy setup
    Time to working version
    ~20 min
    Human minutes
    Not timed. Recorded steps: 2 fix prompts and 1 deploy-setup prompt; the tester created a free Netlify account and access token
    Checks
    10/10
    Bugs
    3 minor
    Plan
    ChatGPT Plus features
    Cost
    $0 usage (inside the subscription)
    More receipt fields
    Receipt ID
    BC-SK1-CODEX
    Status
    Published · TESTED
    Protocol
    v1 rules, general-AI baseline run
    Tool
    ChatGPT Codex
    Benchmark
    SlotKeeper booking app
    Date
    Oct 25, 2026
    Plan in full
    ChatGPT Plus features (a Pro account limited to Plus)
    Model
    GPT-6 Astra, default reasoning
    Cost basis
    Usage $0 within a ChatGPT subscription (Plus features); Netlify free plan
    Relationships
    None
    Retest due
    Dec 24, 2026
    General-AI baseline, not ranked: a Plus-level plan, 2 fix prompts and a human-made hosting account. Bug score under review: 83.5 under our −1-per-minor rule. Source: internal scorecard, recorded Oct 25, 2026. Full review

All receipts, including Cursor's reference run

Read these with the screens

  • The phone and laptop screens are today's live apps (Oct 25, 2026). The checklist results come from each tool's test day.
  • Lovable: Under review: 86.25 if our 5-point critical-bug rule is applied (the scorecard took 4). Corrections.
  • Replit: 87.625 if time counts to the agent's 13-minute finish, which would rank it above Lovable (87.25, or 86.25 under review).
  • ChatGPT Codex: General-AI baseline, not ranked: a Plus-level plan, 2 fix prompts and a human-made hosting account. Bug score under review: 83.5 under our −1-per-minor rule.
  • Design scores come from one reviewer.