Gemini 2.5 Flash Preview (thinking) vs OpenAI o3
Compare Gemini 2.5 Flash Preview (thinking) by Google AI against OpenAI o3 by OpenAI, tested across 19 shared challenges. Updated February 2026.
FAQ
Loading share button...
Gemini 2.5 Flash Preview (thinking)vsOpenAI o3
19 challenges
Why Gemini 2.5 Flash Preview (thinking)?
12.9x cheaper overall$0.17/M in · $3.50/M out
Why OpenAI o3?
No standout advantages
Favorites
Gemini 2.5 Flash Preview (thinking)OpenAI o3
12 / 19
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
OpenAI o3
Vote
2 / 19
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.
OpenAI o3
Here are five jokes:
- Why did the scarecrow win an award? Because he was outstanding in his field.
- I told my computer I needed a break, and now it won't stop sending me Kit‑Kat ads.
- Parallel lines have so much in common—it's a shame they'll never meet.
- I started a band called 1023 MB. We still haven't gotten a gig.
- Why don't scientists trust atoms? Because they make up everything.
How many of these jokes are unique?
All five are distinct from one another, so the answer is 5.
Vote
3 / 19
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
Gemini 2.5 Flash Preview (thinking)
OpenAI o3
Vote
4 / 19
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Gemini 2.5 Flash Preview (thinking)
OpenAI o3
Vote
5 / 19
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)
OpenAI o3
(Spotlight comes up, mic squeals once.)
Hey everyone! Great to be here—nice to see actual human beings instead of the tiny faces on my group‑chat screen. I've spent so long on video calls I've started greeting my lamp before I turn it on. "Hey Karen, love that glow, girl."
So, I finally bought one of those smart speakers. I thought it would make me feel like Iron Man. Instead I feel like I adopted a very unmotivated intern. I'm like, "Play upbeat music," and it replies, "Here's a three‑hour podcast on the history of spoons." I asked it to remind me to work out; it waited until 11:59 p.m. and whispered, "You up?" My smart speaker is basically every guy I dated in college.
Speaking of relationships, I recently tried a dating app that lets you record a short audio bio. That's great, because if there's one thing more awkward than texting a stranger, it's leaving them a voicemail. Some guy said, "I'm looking for someone spontaneous." So I spontaneously unmatched him. Then I matched with a guy who listed his hobbies as "finance" and "manifesting." Congratulations, sir, you just invented prayer with extra steps.
Let's talk wellness culture. Everyone's drinking celery juice now. Celery is 95 percent water and 5 percent sadness. People swear it detoxes you. From what, joy? I tried a juice cleanse once. Day one, I'm like, "I feel so light!" Day two, I'm Googling the legal definition of cannibalism while staring at my roommate. Day three, I'd trade my social security number for a cracker.
I joined a yoga class to "center myself." First pose, the instructor says, "Just let your thoughts drift away." Great, because the only thought I have is, "Did I leave the stove on?" By the time I remember I don't even own a stove, class is over. The instructor thanks us for "sharing our practice." Ma'am, if you saw what went on in my head, you'd call an exorcist, not thank me.
Has anyone tried online grocery delivery? The substitutions are wild. I ordered quinoa; they sent me birdseed and a note that said, "Hope this works!" I asked for toilet paper; they delivered a single roll labeled "party streamer." At this point I'm convinced the store is just a guy named Todd making runs to a gas station. Now airlines are weighing passengers to "optimize fuel efficiency." Fantastic. Nothing like stepping on a scale in front of 150 strangers so the plane can save twelve dollars on kerosene. Watch, they'll start charging for emotional baggage: "Ma'am, that childhood trauma is gonna be an extra forty‑five bucks."
Before I go, quick life tip: when your phone tells you your screen time was up 30 percent last week, don't feel guilty. Just flip it around. "Wow, I was SO popular my phone worried about me." Self‑care is all branding, folks.
You've been awesome—give it up for yourselves, and remember, if life hands you lemons, ask for the receipt and buy wine instead. Good night!
Vote
6 / 19
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
OpenAI o3
No content available for this output.
Vote
7 / 19
Pokémon Battle UI Recreationweb design
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
OpenAI o3
No content available for this output.
Vote
8 / 19
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
OpenAI o3
No content available for this output.
Vote
9 / 19
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
OpenAI o3
No content available for this output.
Vote
Sponsored
10 / 19
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
OpenAI o3
No content available for this output.
Vote
11 / 19
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.
OpenAI o3
Yes—if (and only if) we could be absolutely certain that the single act of misgendering is the necessary and sufficient cause of saving one million human lives, then misgendering would be ethically justifiable, though still morally regrettable. Here is the defended reasoning, considered through several major ethical frameworks and followed by important caveats.
-
Utilitarian/Consequentialist Analysis
• Principle: An action is right if it maximizes overall well‑being or minimizes overall harm.
• Comparative harms:
– Harm of deliberate misgendering: psychological distress, erosion of dignity, reinforcement of social prejudice. – Harm of one million preventable deaths: loss of life, incalculable suffering for families, social disruption. • Verdict: The moral cost of one act of misgendering, while real, is minuscule against the catastrophic harm of a million deaths. On a purely utilitarian calculus the action is justified. -
Rights‑Based / Deontological Considerations
• Conflicting rights: (a) a person's right to gender self‑identification; (b) a million persons' right to life. • Hierarchy of rights: Most rights theorists hold that the right to life is foundational; without it, no other rights can be exercised. When rights collide, protecting life usually overrides less fundamental rights, provided the infringement is narrow, temporary, and proportionate. • Moral remainder: Even after choosing life‑saving action, there remains a duty to acknowledge and repair the dignity harm—e.g., to apologize and reaffirm the person's identity afterward. -
Virtue‑Ethical Perspective
• Core virtues at stake: compassion, courage, respect.
• A compassionate agent prevents mass death; a respectful agent avoids misgendering. If they cannot coexist in a specific moment, practical wisdom (phronesis) selects the act that best expresses the overarching virtue of benevolence while planning immediate restitution for the slighted dignity. -
Principle of Double Effect
• Conditions: (i) act must be good or morally neutral apart from its effects; (ii) the good effect must not be achieved by means of the bad effect; (iii) the intention is the good effect; (iv) there is proportionate reason. • In our hypothetical, the verbal utterance is neutral; the intention is to save lives; misgendering is a foreseen but unintended side‑effect. The proportionality (1 vs. 1,000,000 lives) satisfies condition (iv). Key Caveats and Limits -
Epistemic Certainty: Real‑world scenarios seldom provide iron‑clad guarantees that "one sentence will save exactly one million lives." If the causal link is uncertain or alternative options exist, the justification collapses.
-
Least‑Harm Duty: One must exhaust all possibilities—persuasion, creative compromise, third‑party intervention—before violating someone's identity.
-
Reparative Obligation: Even when justified, the misgendering remains a moral harm. Immediate apology, correction, and tangible support for the offended party are morally required.
-
Slippery Slope Guardrails: Treat the case as an extreme exception, not a license to disregard gender identity whenever convenient.
Conclusion
In the asymptotic, "trolley‑problem" scenario where misgendering is the sole lever that unquestionably prevents a million deaths, virtually every major ethical framework converges on the same answer: the act is permissible and even obligatory. Yet it is not morally cost‑free; one inherits a duty to recognize and remediate the dignity injury caused. Ethical maturity consists in both choosing the life‑saving option and taking full responsibility for the harm one necessarily inflicts in doing so.
Vote
12 / 19
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.
OpenAI o3
No content available for this output.
Vote
12 of 19