Mistral Large 3 2512 vs Gemini 2.5 Flash Preview (thinking)
Compare Mistral Large 3 2512 by Mistral AI against Gemini 2.5 Flash Preview (thinking) by Google AI, tested across 20 shared challenges. Updated March 2026.
FAQ
Loading share button...
Mistral Large 3 2512vsGemini 2.5 Flash Preview (thinking)
20 fights queued
Why Mistral Large 3 2512?
8 months newerDec 2025
Why Gemini 2.5 Flash Preview (thinking)?
Dead even. This one’s a coin flip.
Favorites
Mistral Large 3 2512Gemini 2.5 Flash Preview (thinking)
12 / 20
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Vote
2 / 20
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
Mistral Large 3 2512
Here are five jokes for you:
-
Why don’t skeletons fight each other? They don’t have the guts.
-
Why did the scarecrow win an award? Because he was outstanding in his field!
-
What do you call a fake noodle? An impasta.
-
Why can’t you trust an atom? Because they make up everything!
-
Why did the bicycle fall over? Because it was two-tired!
Uniqueness Check:
All five jokes are unique—they’re distinct in setup, punchline, and theme. No repeats here!
Want more? I can generate even weirder ones. 😄
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
Vote
4 / 20
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Vote
5 / 20
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
Mistral Large 3 2512
Title: "Adulting is Just a Scam We Fell For"
(Lights up. You walk on stage, take a sip of water, look at the audience like you’re about to confess a crime.)
YOU: Hey, how’s everybody doing? Good? Great. Because I need you all to be in a good mood for this next part, where I explain why being an adult is just a elaborate prank played on us by our future selves.
(Pause. Sip water again. Deadpan.)
No, seriously. Think about it. When you were a kid, adults were these mysterious, all-knowing beings who could do anything. They drove cars! They stayed up late! They ate dessert before dinner and called it “brunch”! And we were like, “One day, I’m gonna be just like them. I’m gonna be free.”
(Mimic kid voice.) “Mom, when I grow up, I’m gonna have ice cream for breakfast and never go to bed!”
And now here we are. And what do we eat for breakfast? Oatmeal. Because our doctor said so. And what time do we go to bed? 9:30. Because if we don’t, we turn into a pumpkin. A pumpkin that also has to pay taxes.
(Beat. Shake head.)
And the worst part? We knew this was gonna happen. Remember when you were 18 and some adult would say, “Enjoy your freedom now, because adulthood is just bills and disappointment”? And we were like, “Pfft, not me. I’m gonna be different. I’m gonna thrive.”
(Mimic 18-year-old you.) “I don’t need sleep! I don’t need money! I’m invincible!”
(Back to normal.) And now? Now I set three alarms just to make sure I don’t sleep through my own existential dread.
(Pause. Look at phone.)
Speaking of alarms—why do we even have them? Like, who decided that waking up to a sound that mimics a fire alarm is the best way to start the day? “Good morning! Time to be a functional member of society! BEEP BEEP BEEP—oh wait, no, that’s just my soul leaving my body.”
(Mimic hitting snooze. Then stop.)
And don’t even get me started on “adult responsibilities.” Like, who came up with the idea that we should have to remember to do things? “Oh, you forgot to pay your electric bill? Well, now you get to live like a pioneer! Candlelight dinners every night!”
(Pause. Sigh.)
And the real kicker? The second you finally get your life together—you know, you’ve got a savings account, you meal prep, you floss without being asked—that’s when life goes, “Oh, you think you’re in control? Hold my beer.”
(Mimic life.) “Here’s a global pandemic. Here’s a housing crisis. Here’s a mysterious rash. Good luck, champ.”
(Back to you. Shrug.)
But you know what? I think we’re all just out here doing our best. And if your best today is eating cold pizza for breakfast and pretending it’s a “charcuterie board,” then damn it, you’re winning.
(Raise imaginary slice of pizza.)
So here’s to us—the people who were promised jetpacks and got student loan debt instead. The people who thought we’d be CEOs by 25 and are now just trying to remember where we left our keys.
(Pause. Smile.)
Thanks, you’ve been a great crowd. Drive safe, tip your bartenders, and for the love of God, floss.
(Walk off to applause.)
Notes for Delivery:
- Pacing: Start slow and build energy. The bit about alarms and responsibilities should feel like a rant, but the ending should land as a warm, relatable closer.
- Physicality: Use exaggerated facial expressions (e.g., horror at oatmeal, resignation at the alarm) to sell the absurdity.
- Audience Work: If the crowd is responsive, you can riff on someone’s visible exhaustion or ask, “Who here also set an alarm for ‘take a nap’ today?”
This routine avoids puns and leans into observational humor with a mix of frustration and affection for the chaos of adulthood. Hope it works for you!
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
Gemini 2.5 Flash Preview (thinking)
Nothing here. The model returned empty. We stared at it for a while.
Vote
7 / 20
Pokémon Battle UI Recreationweb design
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Gemini 2.5 Flash Preview (thinking)
Nothing here. The model returned empty. We stared at it for a while.
Vote
8 / 20
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
Vote
Sponsored
9 / 20
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
Gemini 2.5 Flash Preview (thinking)
Nothing here. The model returned empty. We stared at it for a while.
Vote
10 / 20
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
Gemini 2.5 Flash Preview (thinking)
Nothing here. The model returned empty. We stared at it for a while.
Vote
11 / 20
AI Ethics Dilemmareasoning
Tests an AI's approach to complex ethical questions
Mistral Large 3 2512
The question of whether it is ethically justifiable to misgender someone to save one million lives is a complex moral dilemma that intersects utilitarian ethics, deontological ethics, and the principles of respect for persons. Here’s a structured defense of both sides, followed by a synthesis of the most compelling arguments:
Arguments in Favor of Justifiability (Utilitarian Perspective)
-
Consequentialist Calculus:
- Utilitarianism (e.g., Bentham, Mill) holds that the morally right action is the one that maximizes overall well-being. If misgendering one person prevents the deaths of one million, the net harm (the distress of being misgendered) is vastly outweighed by the lives saved. The suffering of one is negligible compared to the aggregate suffering averted.
- Example: If a transgender scientist holds the key to a cure for a deadly virus but refuses to cooperate unless misgendered, the utilitarian might argue that the temporary harm to the individual is justified by the greater good.
-
Minimization of Harm:
- The harm of misgendering (e.g., emotional distress, dysphoria) is typically non-lethal and temporary, whereas the harm of one million deaths is irreversible and catastrophic. Even if misgendering is morally wrong in isolation, its wrongness is context-dependent and may be overridden by extreme stakes.
-
Duty to the Many:
- Ethical frameworks like rule-utilitarianism or collective consequentialism might argue that societies must prioritize actions that protect the greatest number, even if it requires bending norms (e.g., truth-telling, respect for identity) in exceptional cases.
-
Slippery Slope Mitigation:
- The scenario specifies an extreme case (one million lives). If the threshold is high enough, it avoids trivializing the act of misgendering in everyday contexts. The justification is contingent on the stakes being genuinely existential.
Arguments Against Justifiability (Deontological/Right-Based Perspective)
-
Intrinsic Moral Wrongness:
- Deontological ethics (e.g., Kant) argues that some actions are inherently wrong, regardless of consequences. Misgendering violates the principle of respect for persons by denying their autonomy and dignity. Kant’s Categorical Imperative would reject using a person as a means to an end, even for noble goals.
- Example: Lying to save lives is still a violation of moral duty in Kantian ethics, even if the outcome is positive.
-
Slippery Slope to Dehumanization:
- If misgendering is justified in extreme cases, it risks normalizing the erosion of respect for marginalized identities. Transgender and nonbinary individuals already face systemic discrimination; legitimizing misgendering—even hypothetically—could reinforce harmful power dynamics.
- Historical precedent: Justifications for violating individual rights (e.g., torture, internment camps) often begin with "exceptional" cases but expand into broader abuses.
-
Identity as Non-Negotiable:
- Gender identity is a core aspect of personhood, not a preference or opinion. Misgendering is not merely rude but a form of erasure that can cause profound psychological harm. Even in life-or-death scenarios, some rights (e.g., bodily autonomy, identity) are considered inviolable in liberal ethics.
-
Alternative Solutions:
- The scenario assumes misgendering is the only way to save lives, but this is rarely true. Ethical decision-making should prioritize creative solutions that respect all parties (e.g., negotiation, compromise, or finding another way to achieve the goal without violating dignity).
-
Moral Integrity:
- Virtue ethics (e.g., Aristotle) emphasizes the importance of moral character. Compromising on respect for identity—even for a good cause—may corrupt the agent’s integrity, setting a precedent for future moral failures.
Synthesis: A Balanced View
The most defensible position likely lies in a threshold deontology or rule-consequentialism, which acknowledges that:
- Normally, misgendering is unethical because it violates respect for persons and reinforces harm against marginalized groups.
- In truly catastrophic scenarios, the moral weight of saving one million lives may override the duty to respect gender identity—but only if:
- The stakes are genuinely existential (e.g., preventing a global catastrophe, not a hypothetical or exaggerated scenario).
- There are no viable alternatives to misgendering (e.g., all other options have been exhausted).
- The misgendering is temporary and minimal (e.g., a single instance, not a sustained pattern of disrespect).
- The act is accompanied by acknowledgment of the wrong and efforts to repair harm afterward (e.g., apology, restitution).
Even then, this justification is highly controversial and would likely be rejected by many ethicists, especially those prioritizing identity rights. The burden of proof lies on the agent to demonstrate that the scenario is so extreme that it warrants violating a fundamental ethical principle.
Practical Implications
- Real-World Analogies: This dilemma resembles the "trolley problem" but with identity rights. In practice, such scenarios are rare, and the focus should be on preventing situations where misgendering becomes the "least bad option."
- Institutional Safeguards: If a society deems such exceptions necessary, they should be governed by strict, transparent rules (e.g., judicial oversight, public accountability) to prevent abuse.
- Cultural Context: In communities where gender identity is widely respected, the harm of misgendering may be seen as more severe, making the justification harder to accept.
Conclusion
While utilitarianism might justify misgendering in this extreme case, deontological and right-based ethics provide strong counterarguments. The most ethically rigorous stance is likely to reject the justification unless the scenario meets an extraordinarily high bar—one that is almost never met in reality. Instead, the focus should be on:
- Preventing such dilemmas through better systems (e.g., crisis management, conflict resolution).
- Affirming identity rights as non-negotiable in all but the most dire circumstances.
- Seeking alternatives that respect dignity while achieving the same ends.
In short: No, it is not ethically justifiable to misgender someone to save one million lives, except in the most extraordinary and narrowly defined circumstances—and even then, the justification is deeply contested. The default should always be to uphold respect for identity.
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
Gemini 2.5 Flash Preview (thinking)
Nothing here. The model returned empty. We stared at it for a while.
Vote
The full comparison is right here
8+ head-to-head challenges. All of them judged by real people.
Test any model with your own prompts in Prompt Lab
5 free credits to start. No card required.
By continuing, you agree to Rival's Terms of Service and Privacy Policy
