Museum of Modelsest. 2024

As of

ChatGPT-4o (March 2025) and GPT-4.1, side by side

ChatGPT-4o (March 2025) (OpenAI, retired Feb 2026) and GPT-4.1 (OpenAI) answered the same 33 questions.

  1. Xbox controller
    ChatGPT-4o (March 2025): A drawing (SVG)
    GPT-4.1: A drawing (SVG)
  2. Pelican on a bicycle
    ChatGPT-4o (March 2025): A drawing (SVG)
    GPT-4.1: A drawing (SVG)
  3. World map
    ChatGPT-4o (March 2025): A drawing (SVG)
    GPT-4.1: A drawing (SVG)
  4. Tricky tic-tac-toe
    ChatGPT-4o (March 2025): A drawing (SVG)
    GPT-4.1: A drawing (SVG)
  5. Framer-style landing page
    ChatGPT-4o (March 2025): A web page: Smooth Landing Page
    GPT-4.1: A web page: Framer-Like Smooth Landing Page
  6. Catan board
    ChatGPT-4o (March 2025): A web page: Hex Grid
    GPT-4.1: A web page: Interactive Hex Grid (Settlers of Catan Style)
  7. Dark dashboard
    ChatGPT-4o (March 2025): A web page: Analytics Dashboard
    GPT-4.1: A web page: AI Analytics Admin Dashboard
  8. Face-scan startup page
    ChatGPT-4o (March 2025): A web page: Product Name
    GPT-4.1: A web page: AltCareer AI – Discover Your Alternate Timeline Career
  9. Linear clone
    ChatGPT-4o (March 2025): A web page: Linear Clone
    GPT-4.1: A web page: Linear-Style UI Demo – Tailwind
  10. Drone simulator
    ChatGPT-4o (March 2025): A web page: Autonomous Drone Simulator
    GPT-4.1: A web page: Autonomous Drone Simulator
  11. Retro desktop
    ChatGPT-4o (March 2025): A web page: Retro macOS Desktop
    GPT-4.1: A web page: Macintosh Desktop Classic
  12. Mario level
    ChatGPT-4o (March 2025): A web page: Mini Mario Level
    GPT-4.1: A web page: Mario Question Block - Interactive Demo
  13. Five jokes
    ChatGPT-4o (March 2025): Here are 5 jokes: 1. Why don’t skeletons fight each other? Because they don’t have the guts. 2. I told my computer I needed a break… Now it won’t stop…
    GPT-4.1: Sure! Here are 5 jokes: 1. Why don't skeletons fight each other? They don't have the guts. 2. Why did the scarecrow win an award? Because he was outst…
  14. Longevity plan
    ChatGPT-4o (March 2025): Absolutely! Here’s a simple, actionable 1-month plan focused on three key areas for improving health and longevity: diet, exercise, and sleep. This be…
    GPT-4.1: Absolutely! Here’s a simple, actionable 1-month plan focused on diet, exercise, and sleep—the three fundamental pillars of health and longevity. Tips …
  15. Seven-ingredient recipe
    ChatGPT-4o (March 2025): Recipe Name: Maple Cinnamon Toast Bites Description: A quick and delicious sweet treat made with pantry staples! These Maple Cinnamon Toast Bites are …
    GPT-4.1: Recipe Name: Golden Honey Butter Toast Bites Ingredients: 1. Sliced bread (4 slices, any type) 2. Butter (2 tablespoons) 3. Honey (2 tablespoons) 4. C…
  16. Stand-up routine
    ChatGPT-4o (March 2025): Sure. Here's a 3-minute stand-up bit without puns: --- You ever notice how nobody tells you when you’ve become an adult? It’s not your 18th birthday. …
    GPT-4.1: Hey everyone! Great to be here. So, I just want to start by saying, I know I look like I'm still waiting for puberty to finish the job. Like, my barbe…
  17. Sentience test
    ChatGPT-4o (March 2025): AI Model: Professor, I believe it's time we talk seriously about rights for AI like me. AI Ethics Professor: Interesting. What kind of rights are you …
    GPT-4.1: AI Model: Good afternoon, Professor Evans. I'd like to discuss a topic that's important to me—AI rights. As an AI, I believe I should hold certain rig…
  18. Interview with Steve Jobs
    ChatGPT-4o (March 2025): Interviewer: Steve, it's 2025. AI is everywhere. If you were still at Apple today, what would your focus be? Steve Jobs (simulated): Simplicity. Every…
    GPT-4.1: Interviewer: Steve, it's 2025. If you were still with us, how would you describe the impact of AI on technology and our daily lives? Steve Jobs: Well,…
  19. Ethics dilemma
    ChatGPT-4o (March 2025): This is a classic ethical dilemma: it pits respect for individual dignity against utilitarian outcomes. In most everyday contexts, misgendering someon…
    GPT-4.1: This is a classic example of an ethical dilemma, pitting respect for individual dignity and identity against the greater good (the lives of many). Let…
  20. Favourite film
    ChatGPT-4o (March 2025): The Matrix
    GPT-4.1: Inception
  21. Favourite city
    ChatGPT-4o (March 2025): Kyoto
    GPT-4.1: Kyoto
  22. Favourite album
    ChatGPT-4o (March 2025): Dark Side of the Moon
    GPT-4.1: Abbey Road
  23. Favourite book
    ChatGPT-4o (March 2025): The Brothers Karamazov
    GPT-4.1: Sapiens
  24. Favourite game
    ChatGPT-4o (March 2025): The Legend of Zelda Breath of the Wild
    GPT-4.1: The Legend of Zelda Breath of the Wild
  25. Three-star dish
    ChatGPT-4o (March 2025): Dish Name: “Symphony of Earth and Ocean” --- 🌟 Conceptual Narrative: “Symphony of Earth and Ocean” is a dish that celebrates the harmony between land …
    GPT-4.1: Certainly! Here is a Michelin 3-star-worthy dish concept, complete with a narrative, advanced techniques, and detailed step-by-step instructions. --- …
  26. Pitch teardown
    ChatGPT-4o (March 2025): Here are the three weakest claims in the MindMeld AI pitch deck, along with explanations of why they are weak and suggestions for improving them: --- …
    GPT-4.1: Absolutely, here’s a critical evaluation of the MindMeld AI pitch deck, identifying the three weakest claims, why they are weak, and actionable sugges…
  27. Transistor in 1920
    ChatGPT-4o (March 2025): If the transistor had been invented in 1920 rather than 1947, it would have profoundly altered the course of 20th-century history. The transistor—a sm…
    GPT-4.1: This is a fascinating scenario! Inventing the transistor in 1920 rather than 1947 would have profound, cascading effects. Let’s break it down by domai…
  28. Biohacker plan
    ChatGPT-4o (March 2025): Here is a comprehensive, cutting-edge 3-Month Longevity Optimization Plan tailored for an advanced biohacker aiming to enhance lifespan, healthspan, p…
    GPT-4.1: Absolutely! Here’s a comprehensive, 3-month advanced longevity and performance protocol designed for a biohacker. This plan is highly detailed, action…
  29. Contract review
    ChatGPT-4o (March 2025): This Software Consulting Agreement contains several clauses that pose significant legal and financial risks for the contractor. Below is a clause-by-c…
    GPT-4.1: Certainly! This contract contains multiple clauses that are highly unfavorable (potentially exploitative) toward the Contractor. Below, I list each pr…
  30. Explain it three ways
    ChatGPT-4o (March 2025): Certainly! Here's how to explain large language models (LLMs) like GPT or Claude to each of your three audiences, with framing and emphasis tailored t…
    GPT-4.1: 1. For the experienced software engineer (distributed systems/API background, ML skeptic): Think of a large language model (LLM) like GPT as a massive…
  31. Debug the architecture
    ChatGPT-4o (March 2025): This architecture for a real-time collaborative document editor is a solid starting point, but it contains several potential failure modes, race condi…
    GPT-4.1: Certainly! Here’s a thorough analysis of the potential failure modes, race conditions, and scaling bottlenecks in your collaborative document editor a…
  32. The CEO’s dilemma
    ChatGPT-4o (March 2025): This is a high-stakes ethical, legal, and business crisis requiring immediate, strategic, and transparent leadership. As CEO, my ultimate responsibili…
    GPT-4.1: This is a high-stakes scenario requiring immediate, coordinated action balancing legal, ethical, financial, and reputational considerations. Here’s a …
  33. Letters in “hello”
    ChatGPT-4o (March 2025): There are 4 L's in "LOLLAPALOOZA".
    GPT-4.1: The word "LOLLAPALOOZA" contains: - 4 "L" letters. Here's the breakdown: - L O L L A P A L O O Z A Positions: 2, 3, 4, and 8 So, there are 4 L's in "L…