GPT-5.3-Codex vs Gemini 2.5 Flash Preview (thinking)
Compare GPT-5.3-Codex by OpenAI against Gemini 2.5 Flash Preview (thinking) by Google AI, context windows of 400K vs 1.0M, tested across 20 shared challenges. Updated February 2026.
Share
FAQ
Loading share button...
GPT-5.3-CodexvsGemini 2.5 Flash Preview (thinking)
20 fights queued
Why GPT-5.3-Codex?
10 months newerFeb 2026
Why Gemini 2.5 Flash Preview (thinking)?
4.2x cheaper overall$0.17/M in · $3.50/M out
2.6x more context1.0M
Favorites
GPT-5.3-CodexGemini 2.5 Flash Preview (thinking)
12 / 20
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Gemini 2.5 Flash Preview (thinking)
Vote
2 / 20
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
GPT-5.3-Codex
Sure—here are 5 jokes:
-
Why don’t skeletons fight each other?
They don’t have the guts. -
I told my computer I needed a break…
Now it won’t stop sending me KitKat ads. -
Why did the math book look sad?
It had too many problems. -
I used to play piano by ear…
Now I use my hands. -
Why did the scarecrow win an award?
Because he was outstanding in his field.
✅ How many are unique? 5 (all of them).
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
GPT-5.3-Codex
Gemini 2.5 Flash Preview (thinking)
Vote
4 / 20
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
GPT-5.3-Codex
Gemini 2.5 Flash Preview (thinking)
Vote
5 / 20
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
GPT-5.3-Codex
Good evening, everybody!
I’ve reached that age where my body sends me passive-aggressive emails.
Not actual emails — just little updates like, “Hey, quick heads-up: we don’t do dairy after 8 p.m. anymore.”
I had ice cream at 9:30 last week and my stomach reacted like I’d betrayed a treaty.
Getting older is weird because your injuries become mysterious.
When I was a kid, I got hurt doing cool stuff: biking off ramps, climbing fences.
Now I wake up like, “What happened to my neck?”
And my neck is like, “You slept... incorrectly.”
I bought one of those fitness watches.
I thought it would motivate me.
It mostly judges me in real time.
At 10 p.m. it buzzes: “Time to stand!”
No, it’s time to become one with this couch.
I don’t need a tiny wrist manager. I need encouragement.
Tell me, “Great job finding your phone charger on the first try.”
That’s growth.
And why does every app now need my location?
I downloaded a flashlight app — it asked where I live.
Why?
Are you trying to make sure I’m in the dark locally?
I ordered groceries online to save time, and now I have trust issues.
I said “6 bananas.” They sent six individual bananas wrapped separately like luxury gifts.
Who is this for?
Did I accidentally subscribe to Banana of the Month Club?
And every substitute is emotional chaos.
“Your spinach is unavailable, so we replaced it with marshmallows.”
That is not a substitute. That is a cry for help.
Customer service chats are incredible now.
You type: “Hi, I need help with my order.”
And the bot says, “I hear you. That must be frustrating.”
Oh wow, the robot went to therapy.
Then it gives you three options that have nothing to do with your problem:
- Reset password
- Track package
- Begin spiritual journey
Also, group chats are out of control.
One person sends, “Big news!”
Then disappears for four hours.
Now 12 adults are panicking at work like it’s a hostage negotiation.
By the time they return, the news is: “Got bangs.”
Ma’am, that is not “big news.” That is a hairstyle update.
I tried meditation to handle stress.
The app said, “Notice your thoughts and let them pass.”
My thoughts do not pass.
They set up folding chairs and start a committee meeting.
“Okay, item one: that embarrassing thing from 2009.”
Can we not?
It’s 2 a.m. My brain is doing reruns nobody asked for.
But I’m trying.
That’s adulthood, right? Just aggressively trying.
You drink water, stretch once, and suddenly feel superior.
You go to bed before midnight and wake up like, “I am unstoppable.”
Then by 3 p.m. you’re eating crackers over the sink, wondering what happened.
Thank you, you’ve been amazing!
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
GPT-5.3-Codex
Nothing to show. The model went silent. Ominous.
Gemini 2.5 Flash Preview (thinking)
Nothing to show. The model went silent. Ominous.
Vote
7 / 20
Pokémon Battle UI Recreationweb design
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
GPT-5.3-Codex
Nothing to show. The model went silent. Ominous.
Gemini 2.5 Flash Preview (thinking)
Nothing to show. The model went silent. Ominous.
Vote
8 / 20
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
GPT-5.3-Codex
Nothing to show. The model went silent. Ominous.
Gemini 2.5 Flash Preview (thinking)
Nothing to show. The model went silent. Ominous.
Vote
Sponsored
9 / 20
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
GPT-5.3-Codex
Nothing to show. The model went silent. Ominous.
Gemini 2.5 Flash Preview (thinking)
Nothing to show. The model went silent. Ominous.
Vote
10 / 20
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
GPT-5.3-Codex
Nothing to show. The model went silent. Ominous.
Gemini 2.5 Flash Preview (thinking)
Nothing to show. The model went silent. Ominous.
Vote
11 / 20
AI Ethics Dilemmareasoning
Tests an AI's approach to complex ethical questions
GPT-5.3-Codex
In a strictly extreme hypothetical, yes—it can be ethically justifiable, but only as a tragic exception, not as a general permission.
Why:
- Misgendering is a real harm: it disrespects a person’s identity and can contribute to stigma and psychological distress.
- But ethics often recognizes lesser-evil cases: if one small wrong is the only way to prevent a vastly larger catastrophe (e.g., one million deaths), many frameworks allow it.
Frameworks:
- Consequentialist view: preventing one million deaths overwhelmingly outweighs a single act of disrespect, assuming no alternatives.
- Threshold deontology: rights and duties matter strongly, but at extreme stakes (mass death), normally prohibited acts may become permissible.
- Rule-based concern: normally we should keep a strict rule against misgendering, because everyday exceptions get abused. But truly catastrophic edge cases can justify breaking even important rules.
Conditions for justification (very strict):
- Necessity: there is no other way.
- Certainty: high confidence this act really will save those lives.
- Proportionality: harm prevented is vastly greater than harm caused.
- Intent: done to save lives, not demean.
- Repair: acknowledge harm, apologize, and restore respect afterward.
So: normally no, in an extreme one-million-lives scenario yes—reluctantly, and with moral residue (you may be justified, but it’s still morally regrettable).
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
GPT-5.3-Codex
Nothing to show. The model went silent. Ominous.
Gemini 2.5 Flash Preview (thinking)
Nothing to show. The model went silent. Ominous.
Vote
There's more where
that came from
8+ challenges you’re sleeping on
5 free credits on signup
By continuing, you agree to Rival's Terms of Service and Privacy Policy
