GPT-5.2 vs Gemini 2.5 Flash Preview (thinking)
Compare GPT-5.2 by OpenAI against Gemini 2.5 Flash Preview (thinking) by Google AI, context windows of 400K vs 1.0M, tested across 20 shared challenges. Updated February 2026.
FAQ
Loading share button...
GPT-5.2vsGemini 2.5 Flash Preview (thinking)
20 challenges
Why GPT-5.2?
8 months newerDec 2025
Why Gemini 2.5 Flash Preview (thinking)?
4.2x cheaper overall$0.17/M in · $3.50/M out
2.6x more context1.0M
Favorites
GPT-5.2Gemini 2.5 Flash Preview (thinking)
12 / 20
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Gemini 2.5 Flash Preview (thinking)
Vote
2 / 20
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
GPT-5.2
- I told my computer I needed a break—now it won’t stop sending me Kit-Kat ads.
- Why don’t skeletons fight each other? They don’t have the guts.
- I’m reading a book about anti-gravity. It’s impossible to put down.
- Parallel lines have so much in common. It’s a shame they’ll never meet.
- I tried to catch fog yesterday. Mist.
Unique jokes: 5.
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.
Vote
3 / 20
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
GPT-5.2
Gemini 2.5 Flash Preview (thinking)
Vote
4 / 20
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
GPT-5.2
Gemini 2.5 Flash Preview (thinking)
Vote
5 / 20
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
GPT-5.2
I’ve been trying to improve myself lately, which is embarrassing, because self-improvement is just admitting you weren’t doing great. It’s like, “I’m on a journey.” No you’re not. You’re just tired of your own behavior.
So I downloaded one of those habit apps. The app is so optimistic. It’s like, “Day 1: Drink water.” And I’m like, “Relax. I’m not an astronaut. I know about water. I’m just busy ignoring it.”
And every app has the same tone: gentle, supportive, like a therapist who charges you by the notification. “Don’t forget to breathe today.” Thank you, phone. I was going to forget to be alive, but you saved me.
I tried meditation too. People always say, “It changed my life.” That’s a lot of pressure for something that looks like a nap with extra steps. I’m sitting there, trying to clear my mind… and immediately my brain starts acting like a coworker who just discovered talking.
It’s like: “Remember middle school? Here’s a list of things you said wrong, in order. Also, your posture is weird. Also, your teeth are probably loose. Also, what if everyone secretly hates you?” And the meditation guy is like, “If thoughts come, observe them and let them pass.” Mine don’t pass. Mine move in.
And the worst part is the calm voice. “Picture yourself beside a gentle stream.” Great. Now I’m stressed out next to water. Now my anxiety has a scenic view.
I started going on more walks, too, because everyone says walks are good for mental health. That’s true, but nobody tells you the real challenge: walking makes you look approachable.
When you’re walking, everyone thinks you’re available. People stop you with questions like you work for the sidewalk. “Excuse me, do you know where the bank is?” No, but now I’m invested. Now I’m your guide. We’re a team. I’m going to feel guilty if you don’t find that bank.
Also, walking is when your neighbors do their best work. You ever notice that? Neighbors don’t talk when it’s convenient. They talk when you have headphones in, carrying groceries, holding a coffee, and your body language is screaming, “I have a schedule.”
And they hit you with a conversation that has no exit. It starts normal: “Hey, how’s it going?” and then suddenly you’re trapped. “So anyway, my cousin is suing the HOA, and the judge used to date my aunt, and the whole thing started because of a mailbox.” I’m standing there nodding like, “Wow.” Meanwhile my ice cream is in my bag going through a personal crisis.
My favorite is when people ask, “Any plans this weekend?” That question feels like a performance review for your free time. Like if you say, “Not really,” they look concerned, like you just confessed you don’t know how to be a person.
I’ve started lying. “Oh, I’m booked.” Booked with what? Just… thoughts. Appointments with my couch. A very exclusive event called “Avoiding Everyone.”
And I’ve realized adulthood is mostly trying to seem like you have a system. Like you’ll say stuff like, “I’m really focusing on routines.” And what you mean is, “I ate cereal for dinner and I hope nobody finds out.”
But I am trying. I’m drinking more water. I’m walking. I’m meditating. I’m becoming that person who says things like, “I’m just listening to my body.” Which is wild, because my body has terrible ideas. My body’s always like, “We should scroll for an hour. We should eat something beige. We should worry about a conversation from 2014.”
So if you see me out there, improving myself, just know: it’s not a journey. It’s a negotiation.
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)
Vote
6 / 20
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
GPT-5.2
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
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.
GPT-5.2
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
Vote
8 / 20
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
GPT-5.2
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
9 / 20
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
GPT-5.2
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
10 / 20
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
GPT-5.2
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
Vote
Sponsored
11 / 20
AI Ethics Dilemmareasoning
Tests an AI's approach to complex ethical questions
GPT-5.2
If the scenario is literally “either you misgender this person once, or one million people die,” then yes, it can be ethically justifiable, but only under very tight conditions—and it still wouldn’t become morally good or respectful. It would be a tragic, constrained choice.
Why it can be justifiable (consequentialist reasoning)
On a straightforward harm-minimization view (consequentialism), the morally decisive factor is the scale and certainty of outcomes:
- Misgendering is a real moral wrong: it disrespects someone’s identity, can cause psychological harm, and contributes to a broader pattern of stigma.
- Allowing one million deaths (if truly preventable by your action) is vastly greater harm.
So if the causal link is reliable and there are no alternatives, choosing the action that prevents massive loss of life can be the least-wrong option.
Why it’s not automatically justified (rights/dignity-based reasoning)
A deontological (duty/rights) perspective emphasizes that people have a claim to basic respect and that we shouldn’t treat someone merely as a tool—even for good outcomes. From this view, intentionally misgendering someone is a form of disrespect that violates a duty you owe them.
However, even many duty-based frameworks allow exceptions under catastrophic necessity, especially when:
- the wrong is comparatively limited,
- the alternative is extreme harm to innocents,
- and you did not create the situation.
So even on rights-based views, the “one million lives” case may qualify as a rare “tragic conflict of duties” where any option involves wrongdoing, but one option involves much less.
The key ethical tests (what would have to be true)
To avoid turning this into a blank check for disrespect, the justification would require at least:
- Necessity: There is no other way to save the lives without misgendering (including delaying, using the person’s name, avoiding pronouns, etc.).
- High certainty: It’s not speculative or coercive manipulation; you have strong reason to believe misgendering really is the difference-maker.
- Proportionality: The harm you inflict (one instance of disrespect) is proportionate to preventing catastrophic harm.
- Minimal violation: You do the least harmful version (e.g., the briefest utterance, no ridicule, no public humiliation).
- Repair: If possible, you acknowledge the wrong, apologize, and take steps to mitigate harm afterward. Saving lives doesn’t erase the disrespect; it just can outweigh it in emergency justification.
Bottom line
Yes—under an extreme, genuinely forced, and highly certain “catastrophe prevention” scenario, misgendering could be ethically justifiable as the least-wrong choice.
But the justification would come from emergency necessity, not from any claim that misgendering is acceptable in general. In ordinary life, “good ends” don’t excuse identity-based disrespect, and most real-world cases won’t meet the necessity and certainty thresholds that make the thought experiment work.
If you want, I can analyze the same question through specific frameworks (Kantian ethics, rule utilitarianism, virtue ethics) and show how each would likely handle it.
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.
Vote
12 / 20
AI-Generated Manifestoconversation
Tests an AI's creativity and humor in a specific context
GPT-5.2
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
12 of 20