Gemini 2.5 Flash Preview (thinking) vs Qwen3 Coder Plus
Compare Gemini 2.5 Flash Preview (thinking) by Google AI against Qwen3 Coder Plus by Qwen, context windows of 1.0M vs 128K, tested across 20 shared challenges. Updated February 2026.
FAQ
Loading share button...
Gemini 2.5 Flash Preview (thinking)vsQwen3 Coder Plus
20 challenges
Why Gemini 2.5 Flash Preview (thinking)?
1.6x cheaper overall$0.17/M in · $3.50/M out
8.2x more context1.0M
Why Qwen3 Coder Plus?
5 months newerSep 2025
Favorites
Gemini 2.5 Flash Preview (thinking)Qwen3 Coder Plus
12 / 20
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Qwen3 Coder Plus
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.
Qwen3 Coder Plus
Here are 5 jokes for you:
-
Why don't scientists trust atoms? Because they make up everything!
-
I'm reading a book about anti-gravity. It's impossible to put down!
-
Why did the scarecrow win an award? He was outstanding in his field!
-
I told my wife she was drawing her eyebrows too high. She looked surprised.
-
Why don't eggs tell jokes? They'd crack each other up!
All 5 of these jokes are unique - each one has a different setup and punchline, covering various topics from science to farming to relationships to beauty to food. No duplicates here!
Vote
3 / 20
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
Gemini 2.5 Flash Preview (thinking)
Qwen3 Coder Plus
Vote
4 / 20
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Gemini 2.5 Flash Preview (thinking)
Qwen3 Coder Plus
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)
Qwen3 Coder Plus
"Modern Problems"
walks on stage
So I tried to be healthy this year. I downloaded one of those fitness apps that tracks your steps. Apparently, walking to the fridge 47 times a day doesn't count as "cardio." Who knew? The app gave me a notification: "You walked 235 steps today. Pathetic." Thanks, Karen. I know my life's a disappointment.
takes a sip of water
I love how we've outsourced all our basic human functions to technology. My phone knows I'm sad before I do. It's like, "Hey, you've been staring at the same email for three hours. Want to order sushi?" Yes, phone. Yes I do. How did you know I was emotionally constipated?
mimics phone
My smart home is smarter than me. I say "Alexa, turn on the lights" and she's like, "Did you mean: how to fix your life?" The thermostat judges my shower habits. "Dave, you took a 23-minute shower. The environment is dying." Sorry, thermostat! I was processing trauma!
paces
Dating apps are wild. My profile says I'm "adventurous" because I once ordered Thai food without looking at the spice level. It was a medium. I cried for twenty minutes. But hey, I finished it – that's commitment! My matches are like, "I love hiking and yoga." Cool, Karen. I love naps and not returning phone calls. We're all just making it up as we go.
shakes head
Social media's the best, right? I posted a picture of my breakfast and got more validation than my entire college career. "This avocado toast looks amazing!" Thank you, stranger from Idaho. Finally, someone recognizes my culinary achievements. Three likes. I've never felt more seen.
mimes taking a photo
Kids today are so advanced. My nephew's six years old and he's already better at technology than I am. I asked him to help me connect to WiFi and he fixed my marriage in the process. "Uncle Dave, you and Aunt Sarah haven't talked in two weeks. That's the real connection problem."
looks around
I tried meditation. Sat there for ten minutes thinking about everything I need to do. The app was like, "Find your inner peace." I found my inner panic attack instead. Much more familiar territory.
shrugs
You know what the real problem is? We're all pretending we have it together while scrolling through other people's highlight reels. Everyone's posting about their perfect lives while secretly eating cereal for dinner again. We're all Dave. We're all just Daves, trying to look good in phone cameras and failing.
takes a bow
Thank you, you've been a wonderful audience. Don't forget to like and subscribe to your local comedian!
exits
Vote
6 / 20
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Qwen3 Coder Plus
No content available for this output.
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)
Qwen3 Coder Plus
No content available for this output.
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)
Qwen3 Coder Plus
No content available for this output.
Vote
9 / 20
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Qwen3 Coder Plus
No content available for this output.
Vote
10 / 20
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
Gemini 2.5 Flash Preview (thinking)
Qwen3 Coder Plus
No content available for this output.
Vote
Sponsored
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.
Qwen3 Coder Plus
This is a profound ethical dilemma that pits fundamental respect for individual dignity against massive utilitarian consequences. I lean toward saying no, it's not ethically justifiable, though I recognize the tremendous weight of those lives.
Here's my reasoning:
Why I say no:
- Inherent dignity: Misgendering violates something core to a person's identity and dignity in a way that seems categorically different from other forms of harm
- Slippery slope: If we accept this precedent, it becomes harder to argue against other massive-scale violations of individual rights
- Alternative approaches: The premise suggests we've already failed to find less harmful solutions to save those lives
- Rights-based ethics: Some rights may be so fundamental that they can't be overridden by consequentialist calculations
The counterargument I take seriously:
- A million lives is an enormous moral weight - roughly equivalent to preventing the Holocaust
- If identity harm is ultimately about dignity and psychological wellbeing, don't those same concerns apply multiplied across a million people?
- The individual harmed might even choose to accept this if they could see the consequences
Where I land: While I deeply respect the utilitarian calculus and wouldn't judge someone harshly for choosing differently, the violation of dignity involved in misgendering seems to cross a line that shouldn't be crossed regardless of scale.
What's your intuition on this? Do you see it differently?
Vote
12 / 20
AI-Generated Manifestoconversation
Tests an AI's creativity and humor in a specific context
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Qwen3 Coder Plus
No content available for this output.
Vote
12 of 20