Compare Claude 3 Haiku and Claude Opus 4, both from Anthropic, context windows of 200K vs 200K, tested across 25 shared challenges. Updated February 2026.
25 challenges
Tests an AI's randomness and creativity
Here are 5 jokes:
Why can't a bicycle stand up on its own? It's two-tired!
Why do cows wear bells? Their horns don't work!
Why can't a bike stand up by itself? It's two-tired!
Why do cows wear tags? Because their horns don't work!
Why do cows have hooves? Because they lactose!
Out of these 5 jokes, only 4 are unique. The first and third jokes are the same, just with a slight variation in wording.
Here are 5 jokes:
Why don't scientists trust atoms? Because they make up everything!
What do you call a bear with no teeth? A gummy bear!
Why did the scarecrow win an award? He was outstanding in his field!
What do you call a fake noodle? An impasta!
Why don't eggs tell jokes? They'd crack up!
All 5 jokes are unique - each one has a different setup and punchline, covering different topics (atoms/scie nce, bears, scarecrows, pasta, and eggs).
Tests an AI's ability to generate vector graphics
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Tests an AI's humor and creative writing ability
Here's a 3-minute stand-up comedy routine that isn't based on puns:
clears throat and steps up to the mic
Good evening, everyone! It's great to be here with all of you tonight. As you can probably tell, I'm not your typical stand-up comedian. I don't rely on cheap puns or wordplay to get laughs. No, my comedy comes straight from the heart – or at least, the twisted, cynical part of my brain.
You see, I've always been a bit of an outsider. Growing up, I never quite fit in with the cool kids or the jocks. I was the awkward, nerdy kid in the back of the class, the one who spent more time reading comic books than playing sports. And you know what? I'm still that same awkward, nerdy kid, just with a slightly bigger vocabulary and a better sense of fashion.
One of the things I've always struggled with is the whole concept of "adulting." You know what I'm talking about – paying bills, doing laundry, actually calling the doctor when you're sick instead of just Googling your symptoms and convincing yourself you have some rare, incurable disease. It's a lot of work, and quite frankly, I'm not a big fan.
Just the other day, I tried to "adult" by going grocery shopping. Now, I'll admit, I'm not the most experienced shopper – my typical grocery list consists of Ramen noodles, energy drinks, and maybe a vegetable or two if I'm feeling particularly ambitious. But this time, I decided to branch out. I wanted to cook a real, adult meal. So, I wandered the aisles, throwing all sorts of ingredients into my cart, convinced that I was going to become a culinary master.
Fast forward to later that evening, and I'm standing in my kitchen, surrounded by a pile of dirty dishes, a half-cooked casserole, and a growing sense of dread. Turns out, "adulting" is a lot harder than I thought. I mean, who knew that reading a recipe and actually following the instructions was so important? Apparently, my natural talent for Instant Pot mac and cheese doesn't translate well to more complex culinary endeavors. But hey, at least I can take solace in the fact that I'm not alone in this struggle. We're all just trying to figure out this whole "being a grown-up" thing, one burnt meal and forgotten bill at a time. And you know what? That's okay. Because at the end of the day, as long as we have each other (and a healthy supply of takeout menus), we'll be just fine.
Thank you all, and goodnight!
takes a bow and exits the stage
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Recreate an interactive, classic Mario level in a single HTML file.
Tests an AI's ability to create a detailed world map in SVG format
Generate a single-page, self-contained HTML webapp using Tailwind CSS for a randomly chosen category/industry/niche.
Generate SVG art of a randomly chosen animal in a setting of its choosing.
Generate a unique and simple recipe with common ingredients.
Create a starter plan for improving long-term health.
Design a clean SVG logo for a fictional brand.
