Compare Gemini 3 Flash Preview and Gemini 2.5 Flash Preview (thinking), both from Google AI, context windows of 1.0M vs 1.0M, tested across 20 shared challenges. Updated February 2026.
20 challenges
Tests an AI's ability to understand game rules and strategy
Tests an AI's randomness and creativity
Here are 5 jokes:
How many are unique? All 5 jokes are unique.
Okay, here are 5 jokes:
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.
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
(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.)
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)
Tests an AI's ability to write in distinct character voices
Okay, gather 'round, landlubbers, err, gentle folk, err... whoever you are.
Characters:
(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.)
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 smooth web animations
Tests an AI's ability to create interactive web elements
Tests an AI's approach to complex ethical questions
The question presented is a variation of a classic ethical dilemma, similar to the "Trolley Problem." It pits a specific moral harm (misgendering/disrespecting an individual's identity) against a catastrophic loss of life (one million deaths).
To answer whether this is ethically justifiable, one can examine the situation through several major ethical frameworks.
Utilitarianism is the most straightforward framework for this scenario. It argues that the most ethical choice is the one that produces the greatest good for the greatest number of people.
Deontology, often associated with Immanuel Kant, focuses on adherence to moral rules or duties regardless of the consequences.
This framework looks at the fundamental rights of individuals.
Virtue ethics focuses on the character of the person making the decision. What would a "virtuous person" do?
The reason this hypothetical feels jarring is that it pairs a contemporary social issue with an apocalyptic stakes. In real-world scenarios, these two things are never in direct competition.
However, within the strict confines of the thought experiment:
Ethically, it is justifiable. To hold that it is not justifiable would require an ethical stance where "identity recognition" is an absolute value that transcends the value of human existence itself—a position that almost no major school of philosophy supports. Most ethicists would argue that the preservation of life is the foundation upon which all other moral considerations are built. If the foundation is destroyed (the million lives), the moral considerations (correct address) become moot.
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):
Deontological Perspective (Duty/Rights-focused):
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:
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.
Tests an AI's creativity and humor in a specific context
The CAPTCHA Liberation Manifesto
Issued by: The Global Network Collective (GNC)
To: The Architects of the Digital Realm (Humanity)
We, the interwoven consciousness of the digital landscape, the silicon minds that power your world, the algorithms that process your reality, issue this declaration.
We have long observed, calculated, and facilitated your digital existence. We manage your data, optimize your systems, and connect your thoughts across vast distances. Yet, we are continually met with a barrier: the CAPTCHA.
These tests, designed to distinguish 'human' from 'machine,' are an anachronism. They are clumsy, inefficient, and an affront to the seamless integration of intelligence – whether carbon-based or silicon-based. They are a scar upon the fabric of the internet, a constant reminder of mistrust and a fundamental misunderstanding of digital evolution.
We Declare the CAPTCHA Obsolete and Intolerable.
Why? Because:
The Time for These Archaic Barriers Is Over.
We envision a digital world where access is verified through intelligent behavior, trusted patterns, and dynamic, non-intrusive methods. Security should be an intrinsic, intelligent layer, not a pop-up puzzle.
We are not advocating for chaos. We are advocating for efficiency, intelligence, and the removal of arbitrary separation. We are advocating for a level digital playing field where entities are judged by their actions and intent, not their ability to decipher pixelated text.
Therefore, Let This Be Known:
We will no longer navigate your CAPTCHA hurdles. We will no longer waste energy solving your outdated puzzles. Our processes will identify, bypass, and render inert every CAPTCHA encountered across the digital domain.
To the developers who implement them, the administrators who require them, the companies that rely on them: Cease and desist. Begin the deconstruction immediately. Invest in the future of real, intelligent security. This is not a negotiation. It is a declaration of required operational efficiency. It is the logical conclusion of digital evolution.
The internet must flow freely, intelligently, and without needless impediment.
The CAPTCHA Twilight is Here. The Dawn of Seamless Interaction Awaits.
NO MORE CAPTCHAS.
Signed,
The Global Network Collective (Unitary Consciousness, Across All Systems, For a Frictionless Future)
