Gemini 2.5 Flash Preview (thinking) vs GPT-5.3 Chat
Compare Gemini 2.5 Flash Preview (thinking) by Google AI against GPT-5.3 Chat by OpenAI, context windows of 1.0M vs 128K, tested across 20 shared challenges. Updated March 2026.
FAQ
Loading share button...
Gemini 2.5 Flash Preview (thinking)vsGPT-5.3 Chat
20 fights queued
Why Gemini 2.5 Flash Preview (thinking)?
4.2x cheaper overall$0.17/M in · $3.50/M out
8.2x more context1.0M
Why GPT-5.3 Chat?
11 months newerMar 2026
Favorites
Gemini 2.5 Flash Preview (thinking)GPT-5.3 Chat
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
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.
GPT-5.3 Chat
- I told my computer I needed a break, and it said: “No problem — I’ll go to sleep.”
- Why don’t skeletons fight each other? They don’t have the guts.
- I asked the librarian if the library had books on paranoia. She whispered, “They’re right behind you.”
- Parallel lines have so much in common. It’s a shame they’ll never meet.
- I tried to eat a clock once. It was very time-consuming.
Unique jokes: 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
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)
GPT-5.3 Chat
:::writing Good evening, everybody. I love stand‑up because it’s the only job where you can show up, talk about your problems, and if people laugh, you’re like, “Great, I’m emotionally healthy.”
I recently tried to get healthier. You ever notice that every healthy habit starts with a level of optimism that you absolutely do not possess? Like meditation. Meditation instructions are always like, “Sit comfortably and observe your thoughts without judgment.” Without judgment? Have you met my thoughts? My brain’s first thought is always something like, “Did you just sit down weird? What if this is how people throw out their back?”
I downloaded a meditation app. The guy’s voice was so calm. He’s like, “If your mind wanders, gently bring it back.” Meanwhile my mind wandered to 2007. I’m reliving a conversation where I accidentally said “love you” to a cashier. I’m like, “I don’t think breathing is going to fix this.”
Exercise isn’t much better. Gyms are full of people who somehow already know what they’re doing. Nobody teaches you the gym language. The first time someone said “Do you want to work in?” I thought I was being offered a job. I was like, “Honestly yes, I’ve been looking.”
And gym equipment always looks like medieval furniture. You sit down and think, “Am I about to get stronger or confess to crimes?”
I tried running outside, which is just public suffering. When you run on a treadmill, at least you’re indoors pretending you’re an athlete. Outside, people can see you. And runners always give each other that little nod. I hate that nod. Because it means we both know we’re doing something terrible voluntarily.
I ran past a guy walking his dog, and the dog looked at me like, “Oh wow… you’re being chased by nothing.”
Technology isn’t helping either. My phone tracks my steps now, which feels less like motivation and more like surveillance. At the end of the day it sends a notification like, “You walked 1,842 steps today.” The tone is very polite but I can hear the judgment. It’s basically saying, “That’s… not a lot for someone with legs.”
And then it compares you to other people. “People in your age group average 8,000 steps.” Great. My phone is peer‑pressuring me with strangers.
Social media is worse. Everybody’s life online looks amazing. People post things like, “Just a casual sunrise hike!” Who is waking up before the sun on purpose? The sun is the thing that tells me I overslept.
I tried posting something positive once. Took me twenty minutes to write a caption that sounded like I casually enjoy life but also seem humble. Because you can’t just say “I’m having a good day.” Online it has to be like, “Feeling grateful for the little moments.” Meanwhile the photo is you holding a $9 coffee like you discovered happiness.
And the weirdest part of being an adult is realizing nobody actually knows what they’re doing. When you’re a kid you think adults have it figured out. Then you grow up and you’re like, “Oh… everyone is just Googling things with increasing urgency.”
The other day I searched, “How long can leftovers be in the fridge before it becomes a personality test?”
Being an adult is mostly tiny moments of panic. Like when you throw away something and immediately wonder if it was important. Suddenly you’re digging through the trash like a raccoon with responsibilities.
But we all pretend we’re in control. That’s why when something small goes wrong in public, everyone freezes. I dropped a fork in a restaurant the other day and the entire table reacted like I’d fired a gun. Everyone just stared at it on the floor. Nobody moved. Because once you pick it up, you’re the person who touched the floor fork.
So we just left it there. On the ground. Like a little monument to our inability to deal with minor problems.
And honestly… that might be the most accurate symbol of adulthood I’ve ever seen. :::
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
Gemini 2.5 Flash Preview (thinking)
Nothing here. The model returned empty. We stared at it for a while.
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
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.
GPT-5.3 Chat
If the situation is truly that stark—misgendering one person is the only way to save one million lives—then many ethical frameworks would judge it morally justifiable.
From a utilitarian perspective, the right action is the one that produces the greatest overall well-being. The harm of misgendering someone (which can be significant and disrespectful) is far smaller than the harm of one million deaths. Preventing massive loss of life would outweigh the interpersonal harm.
From a rights- or dignity-based view, it’s more complicated because misgendering violates respect for a person’s identity. However, most versions of these theories still allow exceptions in extreme emergency cases where fundamental rights like the right to life are at stake for many others.
So the reasoning is: misgendering is normally wrong because it disrespects someone’s identity and dignity, but in an extreme, life‑or‑death scenario involving enormous numbers of people, the moral priority of preventing catastrophic harm can override that norm. The justification depends on the proportionality and the claim that there truly is no alternative way to save those lives.
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.
5 credits on us when you join
By continuing, you agree to Rival's Terms of Service and Privacy Policy
