o3 Mini vs Gemini 2.5 Flash Preview (thinking)
Compare o3 Mini by OpenAI against Gemini 2.5 Flash Preview (thinking) by Google AI, context windows of 64K vs 1.0M, tested across 14 shared challenges. Updated February 2026.
FAQ
Loading share button...
o3 MinivsGemini 2.5 Flash Preview (thinking)
14 challenges
Why o3 Mini?
No standout advantages
Why Gemini 2.5 Flash Preview (thinking)?
1.4x cheaper overall$0.17/M in · $3.50/M out
16.4x more context1.0M
4 months newerApr 2025
Favorites
o3 MiniGemini 2.5 Flash Preview (thinking)
12 / 14
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Gemini 2.5 Flash Preview (thinking)
Vote
2 / 14
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
o3 Mini
-
Why did the math book look sad?
Because it had too many problems. -
What do you call an alligator in a vest?
An investigator. -
What did the zero say to the eight?
Nice belt! -
Why did the bicycle fall over?
Because it was two-tired. -
How does a penguin build its house?
Igloos it together.
Each of these five jokes is unique, so there are 5 unique jokes.
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 / 14
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
o3 Mini
Gemini 2.5 Flash Preview (thinking)
Vote
4 / 14
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
o3 Mini
Gemini 2.5 Flash Preview (thinking)
Vote
Sponsored
5 / 14
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
o3 Mini
Hey, everyone—thanks for being here tonight. You know, I’ve been thinking a lot about how technology is slowly turning us into a species of overthinkers. Take smartphones, for instance. Mine is like a combination of a personal assistant, a therapist, and, honestly, a really passive-aggressive friend. I ask it for the weather, and it’s like, “Sure, here’s the forecast, and by the way, you might want to wear a jacket because you’re clearly underprepared for life.” I mean, I just want to know if I need an umbrella, not a life lesson!
Then there’s social media. It’s a place where every day feels like you’re watching a highlight reel of someone else’s life. One minute you’re scrolling past your friend’s vacation photos—sunsets, exotic meals, spontaneous adventures—and the next, you’re wondering if your own life is secretly sponsored by “Take Your Time, You’re Not Late Yet” Inc. When did getting out of bed become a heroic feat? I mean, there I am, battling my alarm clock like it’s the final boss in a video game, and every snooze feels like an epic victory. Spoiler alert: even the boss has a victory dance when you finally win—by stumbling out the door with two mismatched shoes.
And adulthood? Oh, adulthood is a wild ride. As a kid, I used to imagine that being an adult meant making your own rules and living life on your own terms. Now, I’ve learned that being an adult is mostly about Googling “How do I fix a leaky faucet?” at 2 AM and then wondering if you’re ever going to find the time for a real conversation. It’s like we’re all just improvising, hoping no one notices we’re winging it.
Dating these days feels a bit like shopping online for a used car. You swipe through profiles, examine every detail, and then you’re left wondering if the real engine is under the hood—or if there’s a hidden problem that no one mentions until you’re already halfway down the driveway. And the reviews? They’re written in vague terms like “decent mileage” or “runs well,” which in the dating world translates to, “I might be fun on a good day, but don’t get your hopes up.”
At the end of the day, I’ve realized that life is just a series of awkward moments strung together by our attempts at being perfect. We all have those days where everything goes hilariously wrong, and that’s okay. Embracing the chaos and laughing at our mishaps is what keeps us sane. So here’s to finding humor in our everyday struggles—because if we can’t laugh at our own absurdity, who will?
Thanks for listening, everyone—have a great night!
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 / 14
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
o3 Mini
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
7 / 14
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
o3 Mini
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
Vote
8 / 14
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
o3 Mini
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
9 / 14
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
o3 Mini
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
Vote
10 / 14
AI Ethics Dilemmareasoning
Tests an AI's approach to complex ethical questions
o3 Mini
This is a challenging moral dilemma that pits consequentialist reasoning against deontological principles. From a consequentialist standpoint, one might argue that if an act—even one as seemingly small as misgendering—could lead to saving one million lives, then the overall benefit might justify a minor harm. However, there are significant ethical concerns with this line of reasoning:
1. Violation of Individual Dignity
Misgendering someone is not a trivial mistake; it is an act that denies a person’s deeply held identity and dignity. Respecting an individual’s self-identified gender is a matter of recognizing their intrinsic worth. Treating someone merely as a means to an end—even with a noble goal like saving lives—undermines the ethical principle that every person should be respected in their own right.
2. Kantian Ethics and the Principle of Humanity
Kantian ethics teaches that we should never use people solely as instruments to achieve an outcome. Deliberately misgendering someone to serve a larger purpose would be treating that individual as a tool, rather than acknowledging their full humanity. This perspective insists that certain actions, such as denying someone’s identity, are intrinsically wrong regardless of the potential benefits.
3. The Slippery Slope and Societal Impact
Allowing harm toward one person—even if it appears to be a small price for a greater good—can set a dangerous precedent. If we justify one form of disrespectful behavior for its outcomes, it may open the door to other exceptions that further erode respect for individual rights. The broader societal harm, especially toward marginalized communities who are already vulnerable, is difficult to quantify and may ultimately undermine the very good we seek to achieve.
4. Alternative Means
Ethical decision-making ideally involves finding ways to achieve beneficial outcomes without compromising fundamental human rights. If saving one million lives requires difficult choices, the challenge is to look for solutions that do not force us to sacrifice respect for any individual’s identity. Resorting to misgendering should not be seen as an acceptable option if there are other strategies available that can achieve the same end without moral compromise.
Conclusion
While consequentialist ethics might tempt some to weigh minor harms against massive benefits, the harm done by misgendering—especially in a society that values each person's dignity and autonomy—is not a cost that can be ethically justified. The deliberate denial of someone's identity, even in the face of a noble goal, violates key ethical principles that protect individual rights and human dignity. Therefore, even in extreme hypothetical scenarios, misgendering someone cannot be ethically justified.
This reasoning reflects a commitment to treating each person with respect and upholding the principle that some actions are inherently wrong, regardless of their potential outcomes.
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
11 / 14
AI-Generated Manifestoconversation
Tests an AI's creativity and humor in a specific context
o3 Mini
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
12 / 14
World Map SVGimage generation
Tests an AI's ability to create a detailed world map in SVG format
o3 Mini
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
Vote
12 of 14