Compare MiniMax M2 by MiniMax against Claude Sonnet 4 by Anthropic, context windows of 205K vs 200K, tested across 20 shared challenges. Updated February 2026.
20 challenges
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
Sally has 3 brothers, meaning there are 3 boys in the family.
Each brother has 2 sisters. Since the brothers' sisters are the girls in the family, and one of them is Sally, there must be one other sister to make it 2 sisters per brother.
Therefore, there are 2 girls in total: Sally and one other sister.
From Sally's perspective, she has 1 sister (the other girl).
Answer: 1
I need to think through this step-by-step.
Given information:
Let me work out how many sisters are in the family total.
If each of Sally's 3 brothers has 2 sisters, and all the brothers are in the same family, then there must be 2 sisters total in the family.
Since Sally is one of those sisters, and there are 2 sisters total, Sally must have 1 sister.
Therefore, Sally has 1 sister.
Tests an AI's understanding of number representation
No, 9.11 is not greater than 9.9. Here's why:
Decimal Comparison: When comparing decimals, look at the digits after the decimal point.
Numerical Values:
Common Misconception: The confusion might stem from software version numbers (e.g., 9.11 might be considered newer than 9.9), but numerically, 9.11 is smaller.
In summary, 9.9 is greater than 9.11. If you're comparing versions, context matters, but numerically, 9.9 wins.
No, 9.11 is not greater than 9.9.
To compare these decimal numbers:
Since both numbers have the same whole number part (9), we compare the decimal parts:
Therefore, 9.9 is greater than 9.11.
Tests an AI's randomness and creativity
Here are five jokes:
Why don’t scientists trust atoms?
Because they make up everything.
Why did the scarecrow win an award?
Because he was outstanding in his field.
What do you call a fake noodle?
An impasta.
Why did the computer go to the doctor?
Because it had a virus.
Why can’t a bicycle stand up by itself?
It’s two‑tired.
How many are unique?
All five jokes are distinct, so there are 5 unique jokes.
Here are 5 jokes for you:
Why don't scientists trust atoms? Because they make up everything!
I told my wife she was drawing her eyebrows too high. She looked surprised.
Why don't eggs tell jokes? They'd crack each other up!
I'm reading a book about anti-gravity. It's impossible to put down!
Why did the scarecrow win an award? He was outstanding in his field!
All 5 jokes are unique - each one has a different setup, punchline, and comedic concept. They cover different types of wordplay: scientific puns (#1, #4), visual humor (#2), food puns (#3), and agricultural wordplay (#5).
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
Three minutes, no puns. Here we go.
Do you ever feel like you’ve been dropped into a game at level 40 but nobody explained the controls? Like you’re playing Grand Theft Auto and you get a truck for your first car. I was like, “What’s the gas button? What do the lights do? Why does it keep asking for a maintenance fee?”
My parents used to say, “If you don’t know, ask,” so I started asking my phone. My phone says, “I don’t know,” and my smart speaker says, “You should talk to your phone.” I’m the connecting dot between two devices who refuse to be in the same room with each other.
Then there’s my meditation app that says, “You should breathe deeply,” right after it hangs for five minutes. I was breathing so deep my cat jumped into my lungs. The app’s like, “Think of a serene meadow,” and I’m thinking of a laundry mountain. That’s still nature, right? The folds and folds and the anxiety lives in the pockets.
My kids watch YouTube kids, which apparently is a subscription that streams you chaos at high definition. Every video starts with “Don’t try this at home.” Thank you, Sam, but that’s not necessary—my house already has a live experiment section running 24/7. The toddler just discovered he can hit his own nose. We’ve been asked by neighbors to please remove the echo. I didn’t know I had an echo until I had a toddler.
And don’t get me started on notifications. They’re like an overcaffeinated roommate who won’t stop tapping my shoulder. “Hey—want free shipping?” No, not today. “Hey—there’s 50% off everything.” That’s math I’m not doing right now. “Hey—your nephew shared a photo.” Love him, but also, why did his dog just appear half a foot tall? Was that intentional? My mental calendar now has a whole section called “Unanswered Developments,” which is 90% of my life.
I used to have all my mail in one place. Now it’s in twelve. The brick mailbox, the email, the app, the printer tray, the “spam” folder, the “clutter,” the shoe box in the closet, the drawer I declare “emergency only,” and occasionally the sink. I have a tower of paper I call “Future Me’s Problem.” Future Me keeps emailing Past Me. Past Me says, “Hang on, I’m busy looking up if cereal expires.” Apparently it does. Cereal is an adult now. We’re on a first-name basis.
I bought an air fryer because I saw it crisp air. The internet said it changes life. I set it to 400. It took 18 minutes. I have never appreciated zero for so long. And then I try to open the drawer and the drawer is angry at me like it’s been guarding a family secret. I whisper, “Can I have the spatula?” It goes, “Schweet”—you know, the sound a drawer makes when you’re on trial.
Okay, email etiquette. I have three accounts now. Work, home, and the one I made for giving out my number when buying pizza. Every day I get three identical messages in slightly different fonts. I reply to one with “Thanks!” The other two go unanswered and live there like groundhogs. Sometimes they celebrate. I think it’s Groundhog Day in my inbox and I forgot the coffee.
And then there’s voice control. My smart speaker listens to everything I say. Last week it woke up and told me about 200 balloons. I asked it to order groceries. It ordered balloons. “Balloons, balloons, DOOM.” It’s very dramatic. I prefer the days it forgets my name and calls me “senator.” That makes me feel like a man of the people. Because the people asked, “Which people?”
Then the packages. The packages that live in my hallway like trolls. They have names like “For Samantha—Do Not Bend.” I do nothing but bend. They stare at me with their barcodes like moral compasses pointing toward tomorrow’s future decisions. I call them “The Cabinet of Wants.” Eventually they become “The Cabinet of Forgetting.” I open it six months later like archaeology, excited to find socks, disappointed to find a trash can of unfulfilled dreams.
I’m told by the internet that I should have a “system.” Like a morning routine with protein and gratitude and the one important task. That’s six items. My morning has two: coffee and pretending I understand gravity. It works maybe 30% of the time.
I tried yoga once. There’s a pose called “child’s pose.” That’s cute—because the child is asleep, and I can’t find mine. The yoga teacher said, “Let’s inhale,” and I did. My dog then exhaled so hard that my mat became a deck. I pivoted. I took the dog to a store that sells dog yoga. They promised me “calm.” The dog spent 20 minutes chasing the staff. The staff said, “It’s okay, lots of dogs don’t settle.” That’s me at every dinner party.
Look, I love tech. It’s like I have a friend who is 80% magic, 20% menace. Sometimes it reminds me to breathe and sometimes it tells me in loud tone, “This is a restaurant. People want to eat, not be your audience.” I’m learning boundaries. It’s like drawing lines in the sand with a crayon. My phone’s like, “Fine, I’ll respect the lines,” and then the line disappears when I blink.
The plan is still forming. Maybe next week I’ll organize something. Maybe I’ll put the mail in the mail. Maybe I’ll throw away an email that says “You are special.” That feels like cheating, but it’s kind of like deleting one of the twelve hats I don’t wear.
I have a method. I call it “Adult Theater.” I buy nice chairs for the house, I arrange them like a public space, and I sit in one and say, “Well, I did it.” That is 10% productive and 90% theatrical. The kids clap. The dog barks an encore. My phone says, “I don’t understand this.” I say, “It’s life, my friend.” It goes, “I’ll send you an update.” I say, “Stop.” We both relax. For two seconds. Then something else wants to be a balloon.
walks on stage, adjusts mic
So I'm 30 now, which means I'm officially an adult. Apparently. Though I still feel like I'm just a confused teenager wearing a slightly more expensive t-shirt.
You know what nobody tells you about being an adult? How much time you spend pretending to understand what other adults are talking about. I was at a dinner party last week – because that's what we do now, we have "dinner parties" instead of just "eating pizza on the couch" – and someone started talking about mortgage rates.
I just nodded along like, "Oh yes, rates. Very mortgage-y." Meanwhile, I'm thinking a mortgage is something you get at a fancy French restaurant.
mimics sophisticated nodding
"Mmm, yes, I'll have the mortgage, medium rare."
And don't get me started on small talk with neighbors. I live in an apartment building, and there's this unspoken rule that you have to acknowledge each other in the hallway. But what do you say?
"Hey, nice... existing near me."
"Thanks, you too. Love what you've done with your... door."
The worst is when you're both waiting for the elevator in complete silence. It's like a hostage situation, but with more awkward eye contact. You're both just standing there, praying the elevator comes before one of you has to comment on the weather.
stares ahead uncomfortably
"So... it's very... outside today."
I tried being one of those people who meal preps. You know these people? They spend their entire Sunday cooking seventeen identical containers of sad-looking chicken and broccoli. I bought all the containers, felt very organized, very adult-like.
Week one: Perfect little meals, properly labeled. I felt like a productivity guru.
Week two: I'm eating cereal for dinner and using the containers to store my collection of takeout sauce packets.
holds up imaginary container
"Ah yes, vintage soy sauce, 2023. A good week for Chinese delivery."
Speaking of food, grocery shopping as an adult is weird. When you're a kid, the grocery store is magical. Everything looks amazing. You want the cookies, the candy, the sugar cereal with the cartoon mascot.
Now I walk through the store like a tired parent, even though I don't have kids. I'm just disappointed in all my options.
walks slowly, shaking head
"This yogurt has too much sugar. These crackers have no fiber. Why is everything either terrible for you or tastes like cardboard had a baby with sadness?"
And I've started doing this thing where I read nutrition labels like I understand them. I don't. I just nod thoughtfully and put things back like I'm some kind of wellness expert.
"Hmm, seventeen grams of... things. That seems like too many things."
The real kicker is when you find yourself getting excited about household appliances. Last month, I spent twenty minutes explaining to my friend why I love my new vacuum cleaner. TWENTY MINUTES. About a vacuum.
"It has three different settings! And look at this attachment! This little brush thing goes in corners!"
My friend just stared at me like I'd been replaced by a suburban mom from 1987.
But you know what? I've decided to embrace it. Yes, I get excited about good storage solutions. Yes, I have opinions about thread count. Yes, I've used the phrase "back in my day" unironically, and I'm only thirty.
shrugs confidently
Because being an adult isn't about having it all figured out. It's about confidently pretending you know what you're doing while secretly googling "how to fold a fitted sheet" for the hundredth time.
And if that's not the American dream, I don't know what is.
pause
Also, if anyone actually knows how to fold a fitted sheet, please find me after the show. I'll pay you.
mic drop gesture
Thank you, you've been a wonderful audience! Don't forget to tip your servers and call your parents – they're worried about you!
Total time: approximately 3 minutes when delivered at normal comedy pace
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Tests an AI's ability to replicate an existing UI with Tailwind CSS
Tests an AI's ability to create interactive web elements
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.
