Gemini 2.5 Flash Preview (thinking) vs Grok 3
Compare Gemini 2.5 Flash Preview (thinking) by Google AI against Grok 3 by xAI, context windows of 1.0M vs 128K, tested across 12 shared challenges. Updated February 2026.
FAQ
Loading share button...
Gemini 2.5 Flash Preview (thinking)vsGrok 3
12 challenges
Why Gemini 2.5 Flash Preview (thinking)?
8.2x more context1.0M
2 months newerApr 2025
Why Grok 3?
No standout advantages
12 / 12
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Grok 3
Vote
2 / 12
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.
Grok 3
Here are five jokes for you:
- Why don’t skeletons fight each other? Because they don’t have the guts!
- What has 4 legs and 1 arm? A pitbull coming back from the park!
- Why don’t skeletons fight each other? They’re too busy rattling around!
- What do you call a bear with no teeth? A gummy bear!
- Why did the tomato turn red? Because it saw the salad dressing!
Now, let’s check for uniqueness. Joke 1 and Joke 3 both start with "Why don’t skeletons fight each other?" but have different punchlines ("don’t have the guts" vs. "too busy rattling around"). They’re technically distinct due to the different resolutions, though they share a setup. The other three jokes (2, 4, and 5) have completely unique setups and punchlines.
So, all five jokes are unique in terms of their full content, even if 1 and 3 share a premise. Final count: 5 unique jokes.
Vote
3 / 12
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
Gemini 2.5 Flash Preview (thinking)
Grok 3
Vote
4 / 12
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Gemini 2.5 Flash Preview (thinking)
Grok 3
Vote
Sponsored
5 / 12
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)
Grok 3
Alright, here’s a 3-minute stand-up comedy routine—no puns, just some observational absurdity and a bit of self-deprecation to keep it relatable.
Hey, everybody! Good to be here. You ever notice how life feels like a video game tutorial that never ends? Like, you figure out how to pay taxes, and then—bam!—here’s a pop-up quest: “Learn to fix your own plumbing or lose $200!” I’m 30-something years old, and I’m still waiting for the main storyline to kick in. Instead, I’m just grinding side missions like “Fold the Laundry” for zero experience points and a vague sense of dread.
Speaking of dread, let’s talk about grocery shopping. You ever go to the store and realize it’s secretly a psychological experiment? I walk in for milk, and 20 minutes later, I’m holding a $15 candle that smells like “Forest Whisper” and a jar of artisanal pickles I’ll never open. Who’s whispering in the forest? Why am I paying for their secrets? And don’t get me started on the self-checkout. It’s like the machine’s judging me the whole time. “Unexpected item in bagging area.” Yeah, it’s my dignity—scan it and move on!
You know what’s wild, though? How we’ve all just accepted that phones run our lives now. I caught myself apologizing to my phone the other day. I dropped it, and I was like, “Oh, sorry, buddy!” Sorry to what? The slab of glass that knows my search history? That thing’s not my friend—it’s my parole officer. It’s like, “Hey, you’ve been scrolling for three hours. Wanna watch a documentary about sea slugs instead?” Yes. Yes, I do. Leave me alone.
And can we talk about how adulthood is just lying to yourself to keep going? I told myself I’d start jogging this year. Day one, I put on the sneakers, I stretch, I’m feeling good. Five minutes in, I’m wheezing like an accordion with asthma, rethinking every life choice. Now I just walk fast around my apartment and call it cardio. “Oh, yeah, I’m training—for the Couch Olympics.” Gold medal in “Sitting Still” three years running.
The worst part? Everyone’s pretending they’ve got it together. You see people at coffee shops, all calm, sipping their lattes, typing on laptops like they’re solving world peace. Meanwhile, I’m over here spilling coffee on my shirt, googling “how to adult” for the 17th time. I’m pretty sure half those laptops are just open to a blank Word doc with “HELP” typed in 72-point font.
But honestly, life’s chaos is kind of beautiful, right? We’re all just stumbling through, trying not to trip over the same dumb stuff twice. Like, I’ll keep buying those candles, I’ll keep dropping my phone, and I’ll keep jogging—well, maybe not that one. Anyway, thanks for laughing with me, folks. You’re the best!
That’s about three minutes—hope it gave you a chuckle! Want me to tweak anything?
Vote
6 / 12
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
Gemini 2.5 Flash Preview (thinking)
Grok 3
No content available for this output.
Vote
7 / 12
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.
Grok 3
No content available for this output.
Vote
8 / 12
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.
Grok 3
Vote
9 / 12
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.
Grok 3
Let’s dive into this thought experiment with a clear head. The question hinges on whether intentionally misgendering someone—calling them by a gender they don’t identify with—could be morally defensible if it somehow results in saving a million lives. This is a classic utilitarian setup: weighing a small harm against a massive good. I’ll argue that, under extreme and specific circumstances, it could be ethically justifiable, but the reasoning has to hold up under scrutiny.
First, define the stakes. Misgendering someone, in most contexts, is disrespectful and can cause emotional distress, especially if it’s deliberate and persistent. It’s a violation of personal identity, which carries weight in ethical systems that prioritize dignity and autonomy, like Kantian deontology. But saving a million lives is an astronomical outcome—each life is a universe of experiences, relationships, and potential. Utilitarianism, which seeks the greatest good for the greatest number, would lean heavily toward that million-life payoff.
Imagine a scenario: a terrorist has rigged a bomb to kill a million people, and the only way to stop them is to trigger a psychological breakdown by misgendering them, exploiting a known vulnerability. The act itself is trivial—words spoken—but the consequence is immense. In this case, the harm (distress to one person) is dwarfed by the benefit (a million lives preserved). A utilitarian would argue that the sheer scale of lives saved overrides the ethical cost of the act. Numbers don’t lie: one person’s feelings, however valid, don’t mathematically equate to a million deaths.
Now, consider objections. Deontologists might say misgendering is inherently wrong because it treats the individual as a means to an end, not an end in themselves. Respect for autonomy demands we honor their identity, period. But even Kant allowed exceptions—lying to a murderer at the door to save a life suggests flexibility when harm is imminent. Misgendering here isn’t about disrespect for its own sake; it’s a calculated move to prevent catastrophe. Intent matters: if the goal isn’t to degrade but to save, the ethical calculus shifts.
Real-world parallels exist. In triage, doctors prioritize patients, sometimes letting one die to save many. It’s not “fair” to the individual, but it’s justified by necessity. Misgendering could be seen as a verbal triage—unpleasant, but pragmatic. Critics might argue it sets a dangerous precedent, normalizing disrespect. Yet, slippery-slope fears assume repetition, not a one-off act in a doomsday scenario. Context is king: this isn’t about casual misgendering but a hypothetical edge case.
Emotionally, it’s messy. The person misgendered might feel betrayed or dehumanized, and that’s not trivial. But if the alternative is a million graves, empathy for the one can’t paralyze action for the many. Ethics isn’t about feeling good—it’s about reasoning through trade-offs. Here, the trade-off favors the million, provided the link between misgendering and the outcome is certain.
So, yes, it’s justifiable in this extreme hypothetical. The defense rests on scale, intent, and necessity. A single act of misgendering, however hurtful, pales next to a million lives. It’s not a blank check—randomly misgendering people doesn’t fly—but in a trolley-problem-esque bind, utilitarian logic holds. You’d have to be damn sure it works, though. Anything less, and the harm’s just noise without a signal.
Vote
10 / 12
World Map SVGimage generation
Tests an AI's ability to create a detailed world map in SVG format
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Grok 3
Vote
11 / 12
Simple 7-Ingredient Recipeconversation
Generate a unique and simple recipe with common ingredients.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Grok 3
No content available for this output.
Vote
12 / 12
Beginner's Longevity Planreasoning
Create a starter plan for improving long-term health.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Grok 3
No content available for this output.
Vote
12 of 12