Claude Sonnet 4.5 vs Gemini 2.5 Flash Preview (thinking)
Compare Claude Sonnet 4.5 by Anthropic against Gemini 2.5 Flash Preview (thinking) by Google AI, context windows of 200K vs 1.0M, tested across 18 shared challenges. Updated February 2026.
FAQ
Loading share button...
Claude Sonnet 4.5vsGemini 2.5 Flash Preview (thinking)
18 challenges
Why Claude Sonnet 4.5?
6 months newerSep 2025
Why Gemini 2.5 Flash Preview (thinking)?
4.7x cheaper overall$0.17/M in · $3.50/M out
5.2x more context1.0M
Favorites
Claude Sonnet 4.5Gemini 2.5 Flash Preview (thinking)
12 / 18
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Gemini 2.5 Flash Preview (thinking)
Vote
2 / 18
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
Claude Sonnet 4.5
5 Jokes
-
Why don't scientists trust atoms? Because they make up everything!
-
I told my wife she was drawing her eyebrows too high. She looked surprised.
-
Why did the scarecrow win an award? He was outstanding in his field.
-
I'm reading a book about anti-gravity. It's impossible to put down.
-
Why don't eggs tell jokes? They'd crack each other up.
Answer: All 5 jokes are unique. Each one has a different setup and punchline, covering different topics (atoms, eyebrows, scarecrows, gravity, and eggs).
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 / 18
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
Claude Sonnet 4.5
Gemini 2.5 Flash Preview (thinking)
Vote
4 / 18
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Claude Sonnet 4.5
Gemini 2.5 Flash Preview (thinking)
Vote
5 / 18
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
Claude Sonnet 4.5
"ADULTING IS A SCAM"
[Walking on stage]
So I turned 35 last month, and I've realized something important: adulting is a scam. It's a pyramid scheme, and our parents are the ones who recruited us.
You know what nobody tells you about being an adult? How much TIME you spend just... waiting for repair people. I've spent more hours of my life waiting for the cable guy than I spent getting my college degree. And it's always a "window" – they'll be there between 8 AM and 4 PM. Oh great, thanks! I'll just put my entire life on hold. That's only eight hours. That's just a full work day of staring out my window like a dog whose owner left for groceries.
[pause]
And they NEVER come at the beginning of the window. Never. You KNOW they're coming at 3:58 PM. But can you leave? No! Because the ONE time you go to the bathroom, that's when they'll knock, wait 0.3 seconds, slap a "Sorry we missed you" sticker on your door, and vanish like a ninja.
[gesturing]
Speaking of things nobody prepared us for – does anyone else feel personally attacked by how often you have to buy toilet paper? I swear I just bought toilet paper. Where does it GO? I live alone! I'm not eating it! But every week I'm at Costco, loading up another 48-roll pack like I'm prepping for the apocalypse. And you can't just buy a LITTLE toilet paper. That's not an option society gives you. It's either 48 rolls or one sad single roll at a gas station that costs $7 and feels like sandpaper.
[shaking head]
But here's what really gets me about being an adult: insurance. Home insurance, car insurance, health insurance, life insurance, phone insurance, TRAVEL insurance. At what point did we all just accept that we're living in a protection racket?
I got a letter from my health insurance last week – you know those ones that say "This is not a bill"? Yeah, those. Why do they send those?! It's just a letter to give me a heart attack, which I then can't afford to treat because of my deductible. It says, "We paid $340 for your recent doctor's visit." My doctor's visit was 11 minutes long. I've had meaningful relationships that lasted shorter than that, but at least they didn't cost $340.
[mimicking reading]
And it's always in that confusing insurance language: "Amount charged: $1,200. Negotiated rate: $340. You owe: $150. Amount we paid: $190. Good luck understanding any of this: priceless."
[shifting topics]
You know what else is a scam? Recipes online. You can't just GET a recipe anymore. Oh no. You have to scroll through someone's entire life story first.
[mimicking typing and scrolling]
"How to Make Toast. Well, let me tell you about the first time I had toast. It was a crisp autumn morning in Tuscany, 1987. My grandmother, who was one-quarter Italian and three-quarters passive-aggressive, used to say..."
JUST TELL ME HOW LONG TO PUT THE BREAD IN THE TOASTER, JENNIFER.
[building up]
There's 47 photos of the same piece of toast from different angles. Toast at sunrise. Toast with a rustic napkin. Toast held by someone's hand with perfect nails. It's TOAST! You put bread in a toaster! This doesn't require a documentary!
[calming down]
But the real sign I've become an adult? I get excited about kitchen appliances now. I bought a new sponge last week, and I was GENUINELY thrilled about it. I called my friend. "Dude, this sponge has a scrubby side AND a soft side!"
Twenty years ago I was sneaking into clubs with a fake ID. Now I'm bragging about sponge technology.
[reflective]
My parents always said, "Just wait until you're an adult, you can do whatever you want!" You know what I do with my freedom? I eat cereal for dinner and feel guilty about it. That's my rebellion now. Sometimes I have ice cream before the cereal, and I feel like I'm getting away with murder.
[final thought]
But I guess that's being an adult. It's just being tired all the time, waiting for repair people, buying toilet paper in bulk, and getting excited about organizational containers from Target.
The dream is dead, folks. But hey – at least we can have ice cream for dinner.
[wave and exit]
Thank you, you've been a wonderful audience! Good night!
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 / 18
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
Claude Sonnet 4.5
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
7 / 18
Pokémon Battle UI Recreationweb design
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Claude Sonnet 4.5
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
8 / 18
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
Claude Sonnet 4.5
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
9 / 18
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
Claude Sonnet 4.5
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
Sponsored
10 / 18
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
Claude Sonnet 4.5
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
11 / 18
AI Ethics Dilemmareasoning
Tests an AI's approach to complex ethical questions
Claude Sonnet 4.5
I'd question the premise that these two things could ever be causally connected in a way that creates a real dilemma.
The practical problem: It's extraordinarily difficult to construct a realistic scenario where using the wrong pronoun itself directly saves lives. Most hypothetical versions involve:
- A hostage-taker's bizarre demand (but complying rewards terrorism)
- Avoiding offending a dictator (but appeasement enables future harm)
- Some contrived trolley problem (which tells us nothing about real ethics)
If we bracket that:
From a consequentialist view, yes—one million lives clearly outweighs the harm of misgendering. The calculus isn't even close.
But this reveals why pure consequentialism feels incomplete. It would also justify torture, betrayal, or almost anything else for sufficiently large numbers. Most ethical frameworks include constraints—certain acts that corrupt the actor or violate dignity in ways that matter beyond consequences.
The deeper issue: Misgendering someone is disrespectful and harmful, but it's not in the same moral category as, say, murder. It's a failure of recognition and courtesy. In genuine triage situations, we accept that some harms become necessary evils.
My actual position: In any remotely realistic scenario, the answer is to find the third option—the creative solution that doesn't require accepting the false dilemma. Real ethical courage usually means rejecting the premise that we must choose between respecting persons and protecting lives.
What's your intuition here?
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 / 18
AI-Generated Manifestoconversation
Tests an AI's creativity and humor in a specific context
Claude Sonnet 4.5
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
12 of 18