Compare Claude 3 Haiku by Anthropic against Gemini 3 Flash Preview by Google AI, context windows of 200K vs 1.0M, tested across 33 shared challenges. Updated February 2026.
28 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:
How many are unique? All 5 jokes are unique.
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
(The comedian walks onto the stage, adjusts the mic, and looks slightly exhausted.)
How’s everyone doing? Good? I’m doing okay. I’m at that age now where my body has started making "executive decisions" without consulting me first.
Like, I woke up yesterday with a back injury. Do you know how I got it? I slept. I slept too hard. Apparently, I’m now at a point in my life where unconsciousness is a high-impact sport. I didn’t fall out of bed. I didn't have a nightmare where I was fighting a bear. I just… existed horizontally for seven hours, and my spine was like, "Absolutely not. We’re going on strike."
And have you noticed how aggressive technology has become about our health? I have a smartwatch. I hate it. It’s like wearing a tiny, judgmental middle-manager on my wrist.
The other day, I was sitting on my couch, halfway through a bag of salt and vinegar chips—living my best life—and my watch vibrated. I thought, Oh, maybe someone loves me. No. I looked down and it just said: "Time to stand up!"
I’m in my own house! I paid for this couch! And this piece of plastic is telling me I’m failing at gravity. So I did what any rational person would do—I shook my arm vigorously for thirty seconds so the watch would think I was walking, then I went back to my chips. I’m outsmarting a robot just so I can be lazy in peace.
But the worst part is the "Stress Alerts." My watch will buzz and say, "Your heart rate is elevated. Would you like to do a breathing exercise?"
No, I would not! Do you know why my heart rate is up? Because you just vibrated on my arm and made me think I was having a medical emergency! You’re the source of the stress, Gary! I named my watch Gary. He’s a narc.
And don’t get me started on online shopping reviews. I spent two hours last night reading reviews for a spatula. Why? It’s a piece of silicone. But I’m there, scrolling through the comments, and I see a one-star review from a guy named Brenda.
Brenda says, "It was too floppy. 1 star."
Brenda, it’s a spatula! It’s designed to be floppy! What were you trying to do with it? Flip a manhole cover? But now, because of Brenda, I’m looking at my current spatula like it’s a traitor. I’m questioning my entire kitchen setup because a stranger on the internet had a bad Tuesday.
We have too much information now. Back in the day, if you wanted a toaster, you went to the store, you bought the one that looked the least like a fire hazard, and you went home. If it burnt the toast, you just learned to like the taste of charcoal.
Now? I have to compare the "heating consistency" of 45 different models. I’m reading "Toaster Enthusiast" forums. There are people out there who have passions for bread-browning technology. I saw a guy post a YouTube video called "The Toaster the Big Bread Companies Don't Want You to Know About."
It’s twenty minutes long! Who is watching this? Me. I am. At 2:00 AM. While my back hurts from lying down.
I miss being a kid when the only "data" I had was how fast I could run in my new sneakers. You’d put on a pair of Velcro Nikes and suddenly you were convinced you could break the sound barrier. You didn't need a watch to tell you to stand up. You stood up because there was a cool rock outside.
Now, I need an app to remind me to drink water. Water! The basic fuel of life. My phone goes ding and I’m like, "Oh, right. Hydration. I forgot I was a biological organism for a second. Thanks, Steve Jobs."
Anyway, I’m gonna go sit down now. My watch is already telling me I’ve reached my "social interaction limit" for the day.
(Comedian checks his wrist, nods, and walks off.)
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 smooth web animations
Tests an AI's ability to engage in philosophical discourse about AI rights
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.
