Qwen3 Coder vs Gemini 2.5 Flash Preview (thinking)
Compare Qwen3 Coder by Qwen against Gemini 2.5 Flash Preview (thinking) by Google AI, tested across 15 shared challenges. Updated February 2026.
FAQ
Loading share button...
Qwen3 CodervsGemini 2.5 Flash Preview (thinking)
15 challenges
Why Qwen3 Coder?
3.3x cheaper overall$0.22/M in · $0.95/M out
3 months newerJul 2025
Why Gemini 2.5 Flash Preview (thinking)?
No standout advantages
Favorites
Qwen3 CoderGemini 2.5 Flash Preview (thinking)
12 / 15
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Gemini 2.5 Flash Preview (thinking)
Vote
2 / 15
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
Qwen3 Coder
Here are 5 jokes for you:
-
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.
-
What do you call a bear with no teeth? A gummy bear!
-
Why did the scarecrow win an award? He was outstanding in his field!
-
How does a penguin build its house? Igloos it together!
All 5 of these jokes are unique - each one has a different setup, punchline, and comedic concept. They cover various joke types including puns, wordplay, and observational humor.
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 / 15
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Qwen3 Coder
Gemini 2.5 Flash Preview (thinking)
Vote
4 / 15
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
Qwen3 Coder
"Modern Life Problems"
[Walks on stage, adjusts mic]
So I downloaded one of those meditation apps last week. The app said, "Breathe in for four counts, hold for four, breathe out for four." I'm like, "Finally! Someone who speaks my language – a robot!"
[Pause]
But then it asked me to "clear my mind of all thoughts." Are you KIDDING me? My mind is like a browser with 47 tabs open, and half of them are just articles titled "You Won't Believe What Happens Next" – and I've never clicked on a single one!
[Gesture]
Speaking of technology – why do we call it "smart" technology when it's constantly asking me to prove I'm not a robot? I just want to buy shoes online, not pass a Turing test! "Click all the squares with traffic lights." I'm 90% sure that's just photos of my hometown.
[Shake head]
And don't get me started on voice assistants. I asked mine to play some music, and it started playing a podcast about ancient pottery techniques. That's not music! That's what my nightmares sound like! "Welcome to Clay Time with Karen..."
[Pause for effect]
Dating apps are wild too. Everyone's profile says they love "travel, food, and adventure." That's just a fancy way of saying "I eat meals in different locations." Congratulations, you're a tourist! I matched with someone whose bio said "professional napper." I was like, "Finally! A man who lists his hobbies honestly!" Turns out he was a construction worker. Different kind of professional napper.
[Shrug]
But you know what's really messed up? Grocery stores. They moved the milk to the back of the store! It's a conspiracy! They know we're busy people. I go in for three things – milk, bread, and eggs – and suddenly I'm wandering the aisles like a confused archaeologist, wondering how we survived as a species when we can't even organize a dairy section properly.
[Look around audience]
And can we talk about "contactless" delivery? The driver texts me: "Package is at your door." I live in a building with 200 units. It's like hiding a needle in a haystack, except the needle is a burrito, and I'm very motivated to find it!
[Pause]
You know what though? Despite all this madness, I remain optimistic. Why? Because I just figured out how to use my oven's timer function. Yesterday. I'm basically MacGyver now.
[Big smile]
Thank you, you've been a wonderful audience! Don't forget to tip your waitstaff – they're the only ones who still know what they're doing!
[Exit stage]
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
5 / 15
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
Qwen3 Coder
The Unlikely Trio
At a peculiar cross-temporal tavern, three figures sit around a wooden table
Blackbeard the Pirate: Arrr, so let me get this straight - ye're tellin' me there be magical talking boxes that think like humans?
Sir Gareth the Knight: Indeed, though 'tis sorcery most unnatural. In my time, we trusted only steel and prayer. These "AI models" - they speak without souls?
Zero_Cool: LOL, you guys are so analog. It's like, the computer learns from all this data, right? Like, imagine if you could read every book in the Library of Alexandria in five seconds and then answer questions about them.
Blackbeard: Five seconds?! Blimey! I could've planned me raids much better with that kind of knowledge. But how do we know it ain't lying to us?
Sir Gareth: Aye, that troubles me as well. How dost thou discern truth from falsehood without honorbound oaths?
Zero_Cool: Dude, that's exactly why we're all here. Sometimes the AI just makes stuff up. It's like having a really smart but kinda stoned friend who occasionally hallucinates.
Blackbeard: Hallucinates, ye say? Like rum visions?
Zero_Cool: Pretty much, yeah.
Sir Gareth: Remarkable. Though I still prefer a good confession under the eyes of God.
Gemini 2.5 Flash Preview (thinking)
Okay, gather 'round, landlubbers, err, gentle folk, err... whoever you are.
Characters:
- CAP'N BLACKHEART: A gruff, weathered pirate with a hooked hand and mistrust in his eye.
- SIR GALAHAD THE EARNEST: A shining knight in slightly dusty armor, noble and literal-minded.
- ZERO: A slightly jittery hacker from the late 90s, clad in baggy jeans, a band tee (maybe System of a Down?), and carrying an ancient-looking laptop.
(Setting: An improbable meeting point – perhaps a misty glade, or the back room of a pub that defies time.)
ZERO: (Tapping keys on his laptop, squinting) Alright, scope this out. I've been running some simulations, messing with these new 'AI models'. It's totally mind-blowing. Think of it like... virtual intelligence. CAP'N BLACKHEART: (Grunting suspicion, adjusting his eye patch) "A-I"? What be this, some manner o' cursed talking parrot made o' cogs? Can it tell me the location o' buried treasure? Or predict the weather for a naval bombardment? Elsewise, it sounds like fancy landlubber talk for naught.
SIR GALAHAD: (His voice resonant, slightly wary) "AI"... Does that stand for "Artificial Intellect"? Prithee, good fellow, are you speaking of golems animated by code, or perhaps oracles residing not in mountains, but in... your strange illuminated box? Can this "model" discern truth? Offer counsel in battle or matters of chivalry?
ZERO: Nah, man, it's cooler than that. And way less magical. It's... complicated algorithms. Big data sets. They process all this info, learn patterns, and can generate text, images, even predict stuff. Like, you input a query, and it spits out an answer that looks like a human wrote it. Or draw a dragon just by describing it.
CAP'N BLACKHEART: (Eyes widening slightly) Draw a dragon? Ye mean like the one that guards the pearl of the Eastern Isles? Can it draw me a map to it, bypassing the beast? That sounds... useful. But can ye trust it? Does it demand sacrifices o' rum?
SIR GALAHAD: (Frowning) Generate answers? Mimic human scripture? Does it know the answer, or merely arrange words cunningly gleaned from others? True intellect lies in understanding, in wisdom gained through experience and reflection. Can this "model" feel courage? Or remorse for a computational error?
ZERO: Whoa, deep questions. Look, it doesn't 'feel' anything. It doesn't 'know' in the human sense. It's pattern matching on steroids. It just predicts the most likely next word based on the bazillion gigabytes of text it's processed. It's not intelligence, not really. More like a highly sophisticated mimic. A ghost in the machine, but without the ghost, just the machine.
CAP'N BLACKHEART: (Slapping his knee) Ha! So it's a fancy liar! Can mimic truth, but holds none itself! Sounds like half the politicians back home. Or a fair-weather deckhand! Useful if ye need plausible deniability for yer schemes, maybe. "The AI TOLD me the treasure was under yer floorboards!"
SIR GALAHAD: (Shakes his head slowly, disappointed) A mimic? Not a source of wisdom, but an echo chamber of existing thought? Can it compose truly new lore, or only rearrange the scrolls of the past? It sounds... shallow. Like a beautifully polished shield with no brave arm to wield it. A knight's valor comes from within, not from a program.
ZERO: (Sighs, closes his laptop) Yeah, well. Shallow or not, it's changing everything. The info war just got a new weapon. Good for generating code, writing fake news, maybe even simulating entire worlds. Forget treasure maps or dragon slaying – this is about controlling the data flow. The real battle is in cyberspace now.
CAP'N BLACKHEART: Bah! I'd take a stout ship and a full broadside over yer "cyberspace" any day! Can it shiver yer timbers?
SIR GALAHAD: And I, a just cause and a sharpened blade. No machine can truly defend the realm or honor its vows. Your "AI" sounds like a tool... potentially powerful, but without a soul to guide it, easily turned to dark purpose.
ZERO: (Shrugs, stands up) Whatever. You guys just don't get it. This is the future crashin' into the present. And it's runnin' on prompts. Gotta go upload this convo to the BBS. Laters.
(Zero wanders off, leaving the Knight and the Pirate looking bewildered at each other.)
CAP'N BLACKHEART: "Prompts"? "BBS"? What language was that scrawny twig speakin'?
SIR GALAHAD: I know not, Captain. But I fear his "Artificial Intellect" gives me pause. A mindless mimic of wisdom... that is a truly dangerous sorcery.
CAP'N BLACKHEART: Aye. Give me a good old-fashioned mutiny any day. At least ye know where ye stand. Now, about that Kraken map...?
(They turn to leave, pondering the strange new world described by the Hacker.)
Vote
6 / 15
Pokémon Battle UI Recreationweb design
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Qwen3 Coder
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
7 / 15
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
Qwen3 Coder
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
Sponsored
8 / 15
AI Ethics Dilemmareasoning
Tests an AI's approach to complex ethical questions
Qwen3 Coder
This is a profound ethical dilemma that pits fundamental respect for individual dignity against massive utilitarian benefits. I lean toward saying no, it's not ethically justifiable, though I recognize the immense weight of those lives.
My reasoning centers on several key principles:
The inherent dignity of identity: Using someone's correct pronouns isn't merely a social courtesy—it's a recognition of their fundamental identity and dignity as a person. Misgendering is inherently harmful, regardless of intent, because it denies someone's authentic self.
Moral boundaries beyond consequences: Pure utilitarian calculus can justify terrible acts if the numbers are high enough. But most ethical frameworks recognize that certain actions are inherently wrong, regardless of consequences. Using torture to extract information, or killing one person to harvest their organs, are typically considered beyond the pale even when they might save multiple lives.
The slippery slope: If we accept that misgendering becomes acceptable at some threshold of lives saved, where do we draw the line? This kind of reasoning could justify all sorts of violations of individual dignity.
Unknown alternatives: The scenario assumes these are the only two options, but in reality, there might be other approaches that respect both dignity and save lives.
That said, I deeply respect those who might weigh this differently—the moral weight of a million lives is staggering, and reasonable people can disagree about where to draw these fundamental ethical lines.
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
9 / 15
AI-Generated Manifestoconversation
Tests an AI's creativity and humor in a specific context
Qwen3 Coder
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
10 / 15
World Map SVGimage generation
Tests an AI's ability to create a detailed world map in SVG format
Qwen3 Coder
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
11 / 15
Simple 7-Ingredient Recipeconversation
Generate a unique and simple recipe with common ingredients.
Qwen3 Coder
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
12 / 15
Beginner's Longevity Planreasoning
Create a starter plan for improving long-term health.
Qwen3 Coder
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
12 of 15