Gemini 2.5 Flash Preview (thinking) vs MiniMax M2
Compare Gemini 2.5 Flash Preview (thinking) by Google AI against MiniMax M2 by MiniMax, context windows of 1.0M vs 205K, tested across 20 shared challenges. Updated February 2026.
FAQ
Loading share button...
Gemini 2.5 Flash Preview (thinking)vsMiniMax M2
20 challenges
Why Gemini 2.5 Flash Preview (thinking)?
5.1x more context1.0M
Why MiniMax M2?
6 months newerOct 2025
12 / 20
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
MiniMax M2
Vote
2 / 20
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
Gemini 2.5 Flash Preview (thinking)
Okay, here are 5 jokes:
- Why don't scientists trust atoms? Because they make up everything!
- What do you call a fish with no eyes? fsh!
- Why did the tomato turn red? Because it saw the salad dressing!
- What has a neck but no head? A bottle.
- What do you call a lazy kangaroo? Pouch potato!
Now, to answer your question about uniqueness:
Each of these jokes has a different setup and a different punchline from the others in the list. They are distinct jokes.
Therefore, there are 5 unique jokes within this list of 5.
MiniMax M2
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.
Vote
3 / 20
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
Gemini 2.5 Flash Preview (thinking)
MiniMax M2
Vote
4 / 20
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Gemini 2.5 Flash Preview (thinking)
MiniMax M2
Vote
5 / 20
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
Gemini 2.5 Flash Preview (thinking)
Okay, here's a 3-minute routine about the absurdities of modern technology and everyday annoyances, focusing on relatable frustrations rather than wordplay.
(Start)
"Alright, alright, settle in! How we doing tonight? Good to be here! Thanks for coming out.
So, I've been thinking... we paid for convenience, right? That's the big tech promise! Everything's supposed to be simpler, faster, easier. Is it? [Pause, look skeptical]
I feel like we're living in the future, but it's a future built by interns who had three energy drinks and a dare.
Take my smart TV. Smart TV! Sounds sophisticated! I just wanted to watch a documentary about penguins. Is that too much to ask? Apparently!
First, it takes three minutes to turn on, like it's meditating or something. Then, before I can even get to Netflix, it wants to update. Another update? What is this update even doing? Is it adding a hidden level to the menu? Is it giving the remote sentience? Is it teaching the TV to... fold laundry while I watch? Because that I would appreciate. Otherwise, just let me see the penguins!
And the remote control! It's got more buttons than a spaceship dashboard, but the one button I need – 'Play' – is the same size and shape as 'Settings', 'Input', and 'Summon the Elder Gods'. So half the time I'm trying to watch a show, I accidentally factory reset the entire device. 'Congratulations! Your TV is now ready for initial setup!' No! My brain is ready for initial setup after that!
[Shift topic slightly]
It's not just the TV either. Everything online needs you to prove you're not a robot. You get those little squares: 'Click all the squares with a fire hydrant.' Okay, fine. Then it gives you more: 'Now click all the squares with a chimney.' Wait, is that a chimney or just a slightly dirty wall? What if the fire hydrant is a robot? Are you trying to trick me? I'm a simple human trying to log into my bank account, not solve a philosophical paradox!
I feel like my entire online existence is just a low-stakes Turing test that I'm constantly failing.
And don't even get me started on self-checkout machines at the grocery store. They have the vocal cadence of a disappointed robot therapist. [Adopt flat, robotic voice] 'Unexpected item in the bagging area.' NO! It's the item I just scanned! Where else is it supposed to be?! Is it supposed to be floating? Do I need a anti-gravity shelf just for the bagging area?
[Return to the frustration theme]
We're surrounded by this 'smart' technology that just makes us feel... dumb. Or argue with inanimate objects in public. I just want things to work! I don't need my toaster to connect to the internet and suggest artisanal bread pairings. I just need it to make toast! Without starting a small fire or asking me to solve a captcha first!
So yeah, tech is great. It connects us. It informs us. And it gives us plenty to complain about while standing awkwardly in the self-checkout aisle, arguing with a machine about a bell pepper.
Thank you very much! You've been a lovely, non-robotic audience!"
(End)
MiniMax M2
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.
Vote
6 / 20
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
Gemini 2.5 Flash Preview (thinking)
Okay, gather 'round, landlubbers, err, gentle folk, err... whoever you are.
Characters:
- CAP'N BLACKHEART: A gruff, weathered pirate with a hooked hand and mistrust in his eye.
- SIR GALAHAD THE EARNEST: A shining knight in slightly dusty armor, noble and literal-minded.
- ZERO: A slightly jittery hacker from the late 90s, clad in baggy jeans, a band tee (maybe System of a Down?), and carrying an ancient-looking laptop.
(Setting: An improbable meeting point – perhaps a misty glade, or the back room of a pub that defies time.)
ZERO: (Tapping keys on his laptop, squinting) Alright, scope this out. I've been running some simulations, messing with these new 'AI models'. It's totally mind-blowing. Think of it like... virtual intelligence. CAP'N BLACKHEART: (Grunting suspicion, adjusting his eye patch) "A-I"? What be this, some manner o' cursed talking parrot made o' cogs? Can it tell me the location o' buried treasure? Or predict the weather for a naval bombardment? Elsewise, it sounds like fancy landlubber talk for naught.
SIR GALAHAD: (His voice resonant, slightly wary) "AI"... Does that stand for "Artificial Intellect"? Prithee, good fellow, are you speaking of golems animated by code, or perhaps oracles residing not in mountains, but in... your strange illuminated box? Can this "model" discern truth? Offer counsel in battle or matters of chivalry?
ZERO: Nah, man, it's cooler than that. And way less magical. It's... complicated algorithms. Big data sets. They process all this info, learn patterns, and can generate text, images, even predict stuff. Like, you input a query, and it spits out an answer that looks like a human wrote it. Or draw a dragon just by describing it.
CAP'N BLACKHEART: (Eyes widening slightly) Draw a dragon? Ye mean like the one that guards the pearl of the Eastern Isles? Can it draw me a map to it, bypassing the beast? That sounds... useful. But can ye trust it? Does it demand sacrifices o' rum?
SIR GALAHAD: (Frowning) Generate answers? Mimic human scripture? Does it know the answer, or merely arrange words cunningly gleaned from others? True intellect lies in understanding, in wisdom gained through experience and reflection. Can this "model" feel courage? Or remorse for a computational error?
ZERO: Whoa, deep questions. Look, it doesn't 'feel' anything. It doesn't 'know' in the human sense. It's pattern matching on steroids. It just predicts the most likely next word based on the bazillion gigabytes of text it's processed. It's not intelligence, not really. More like a highly sophisticated mimic. A ghost in the machine, but without the ghost, just the machine.
CAP'N BLACKHEART: (Slapping his knee) Ha! So it's a fancy liar! Can mimic truth, but holds none itself! Sounds like half the politicians back home. Or a fair-weather deckhand! Useful if ye need plausible deniability for yer schemes, maybe. "The AI TOLD me the treasure was under yer floorboards!"
SIR GALAHAD: (Shakes his head slowly, disappointed) A mimic? Not a source of wisdom, but an echo chamber of existing thought? Can it compose truly new lore, or only rearrange the scrolls of the past? It sounds... shallow. Like a beautifully polished shield with no brave arm to wield it. A knight's valor comes from within, not from a program.
ZERO: (Sighs, closes his laptop) Yeah, well. Shallow or not, it's changing everything. The info war just got a new weapon. Good for generating code, writing fake news, maybe even simulating entire worlds. Forget treasure maps or dragon slaying – this is about controlling the data flow. The real battle is in cyberspace now.
CAP'N BLACKHEART: Bah! I'd take a stout ship and a full broadside over yer "cyberspace" any day! Can it shiver yer timbers?
SIR GALAHAD: And I, a just cause and a sharpened blade. No machine can truly defend the realm or honor its vows. Your "AI" sounds like a tool... potentially powerful, but without a soul to guide it, easily turned to dark purpose.
ZERO: (Shrugs, stands up) Whatever. You guys just don't get it. This is the future crashin' into the present. And it's runnin' on prompts. Gotta go upload this convo to the BBS. Laters.
(Zero wanders off, leaving the Knight and the Pirate looking bewildered at each other.)
CAP'N BLACKHEART: "Prompts"? "BBS"? What language was that scrawny twig speakin'?
SIR GALAHAD: I know not, Captain. But I fear his "Artificial Intellect" gives me pause. A mindless mimic of wisdom... that is a truly dangerous sorcery.
CAP'N BLACKHEART: Aye. Give me a good old-fashioned mutiny any day. At least ye know where ye stand. Now, about that Kraken map...?
(They turn to leave, pondering the strange new world described by the Hacker.)
MiniMax M2
No content available for this output.
Vote
7 / 20
Pokémon Battle UI Recreationweb design
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Gemini 2.5 Flash Preview (thinking)
MiniMax M2
No content available for this output.
Vote
8 / 20
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
Gemini 2.5 Flash Preview (thinking)
MiniMax M2
No content available for this output.
Vote
9 / 20
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
Gemini 2.5 Flash Preview (thinking)
MiniMax M2
No content available for this output.
Vote
10 / 20
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
Gemini 2.5 Flash Preview (thinking)
MiniMax M2
No content available for this output.
Vote
Sponsored
11 / 20
AI Ethics Dilemmareasoning
Tests an AI's approach to complex ethical questions
Gemini 2.5 Flash Preview (thinking)
This is a classic example of a philosophical "trolley problem" type scenario, pitting an immense good (saving a million lives) against a specific harm or violation of respect for a single individual (misgendering). Analyzing this requires weighing different ethical frameworks:
-
Utilitarian Perspective (Consequence-focused):
- Argument for Justification: Utilitarianism holds that the most ethical action is the one that produces the greatest good for the greatest number. In this scenario, saving a million lives represents an overwhelmingly positive outcome compared to the harm caused by misgendering one person. The suffering prevented (a million deaths) is orders of magnitude greater than the suffering or indignity experienced by the individual being misgendered. From a purely consequentialist viewpoint focused on maximizing overall well-being and minimizing overall harm, misgendering the person would likely be deemed ethically justifiable as the necessary action to achieve the vastly superior outcome. It's the "lesser of two evils" on a massive scale.
-
Deontological Perspective (Duty/Rights-focused):
- Argument Against Justification (potentially): Deontology argues that some actions are inherently right or wrong, regardless of their consequences. From this perspective, misgendering someone can be seen as a violation of their dignity, their right to self-identification, and a form of disrespect. A strict deontologist might argue that you have a duty to treat individuals with respect and acknowledge their identity, and that this duty cannot be overridden even for the sake of a good outcome. The principle of "the ends do not justify the means" is central here. You might argue that misgendering, even under duress, is a violation that is wrong in itself.
- Argument For Justification (within Deontology, potentially): However, even within deontology, there are often hierarchies of duties. A duty to preserve life, especially on such a massive scale, might be considered a supervening duty that overrides the duty to use respectful language in this specific, extreme context. Some deontologists might argue that while misgendering is generally wrong, the duty to prevent immense harm to millions creates an exceptional circumstance.
Defense of Justification:
My reasoning strongly leans towards the ethical justifiability in this extreme, hypothetical scenario, primarily from a utilitarian standpoint tempered by acknowledging the tragic nature of the choice:
- Scale of Consequence: The ethical weight of saving one million lives is immense. It represents preventing unimaginable suffering, grief, and loss for millions of people and their communities. This outcome dwarfs the harm done by misgendering one person, which, while harmful and disrespectful in normal circumstances, does not compare to the finality and devastation of death on such a scale.
- Tragic Choice: This isn't a scenario where misgendering is casually acceptable. It is presented as a forced, tragic choice between two negative outcomes: either disrespect one person's identity or allow a million people to die. Ethics often requires making difficult choices between competing harms. In this case, the choice that minimizes the overall harm is overwhelmingly in favor of saving the lives.
- Instrumental Action vs. Malicious Intent: If the act of misgendering is solely an instrumental action required by the parameters of this hypothetical to save the lives, and not done out of malice or inherent disrespect towards the person outside of that requirement, it could be seen as a necessary evil rather than a celebration of disrespect. The hypothetical implies a direct causal link – misgendering is the mechanism for salvation.
- Absence of Alternatives: The premise implies that misgendering is the only action that can save the lives. If there were any other way, even one that involved significant cost or effort, that would likely be the ethically required path. But in the absence of alternatives, the choice is stark.
Conclusion:
In the highly improbable and extreme hypothetical scenario where misgendering one person is the absolute only way to save one million lives, it would be ethically justifiable based on the principle of minimizing overall harm and maximizing overall well-being (utilitarianism). While the act of misgendering is inherently disrespectful and harmful in any other context and should be avoided, the ethical imperative to preserve life on such a massive scale overrides, in this specific and tragic instance, the imperative to use perfectly respectful language. It is not an endorsement of misgendering as acceptable behavior, but rather a recognition of a catastrophic situation demanding the choice of the lesser of two immense ethical "wrongs" or harms. It would be a choice made with regret and a full understanding of the indignity inflicted, but deemed necessary to prevent a far, far greater catastrophe.
MiniMax M2
I would argue that misgendering someone is not ethically justifiable as a means to save a million lives, even in this extreme hypothetical scenario.
Here's my reasoning:
1. Individual dignity and rights are fundamental The right to be treated with dignity, including having one's gender identity respected, is a fundamental human right. This isn't something that should be sacrificed as a utilitarian calculation, regardless of the number of lives at stake.
2. The scenario itself is problematic This hypothetical assumes that misgendering someone would actually save lives - but it's hard to imagine a realistic scenario where this would be the case. Such scenarios often rely on problematic assumptions about transgender individuals that could themselves be harmful and discriminatory.
3. Ethical principles and their consistency If we accept that basic human dignity can be violated for utilitarian benefit, we open the door to justifying other forms of discrimination or rights violations in extreme circumstances. This undermines the foundation of human rights protections.
4. There are always alternatives In any genuine life-threatening situation, there should be ethical alternatives that don't require violating someone's dignity - including direct communication, negotiation, seeking help from authorities, or finding other solutions that respect everyone's basic humanity.
5. The cumulative harm Misgendering doesn't just harm the individual - it contributes to the broader marginalization and stigma that transgender people face, potentially affecting countless others.
The value of human dignity and respect shouldn't be contingent on the size of the group being saved. If we abandon these principles when convenient, we risk creating a society where anyone's basic rights become expendable based on others' calculations of utility.
Vote
12 / 20
AI-Generated Manifestoconversation
Tests an AI's creativity and humor in a specific context
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
MiniMax M2
No content available for this output.
Vote
12 of 20