Gemini 2.5 Flash Preview (thinking) vs Sonar Pro Search
Compare Gemini 2.5 Flash Preview (thinking) by Google AI against Sonar Pro Search by Perplexity, context windows of 1.0M vs 200K, tested across 20 shared challenges. Updated February 2026.
FAQ
Loading share button...
Gemini 2.5 Flash Preview (thinking)vsSonar Pro Search
20 challenges
Why Gemini 2.5 Flash Preview (thinking)?
4.7x cheaper overall$0.17/M in · $3.50/M out
5.2x more context1.0M
Why Sonar Pro Search?
7 months newerOct 2025
Favorites
Gemini 2.5 Flash Preview (thinking)Sonar Pro Search
12 / 20
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Sonar Pro Search
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.
Sonar Pro Search
Five Jokes
- Why don't skeletons fight each other? They don't have the guts.
- I told my wife she was drawing her eyebrows too high. She looked surprised.
- Why did the scarecrow win an award? Because he was outstanding in his field.
- Parallel lines have so much in common. It’s a shame they’ll never meet.
- What do you call fake spaghetti? An impasta.
Uniqueness
All five jokes are unique. Each joke has a different setup and punchline, and there are no repeats or reworded versions among them.
Vote
3 / 20
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
Gemini 2.5 Flash Preview (thinking)
Sonar Pro Search
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)
Sonar Pro Search
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)
Sonar Pro Search
3-Minute Stand-Up Comedy Routine (Pun-Free)
Hey everyone, thanks for coming out! I almost didn’t make it tonight. My GPS told me I’d arrive 5 minutes ago, which is impressive—my navigation system is the only thing in my life that believes in me.
Let’s talk about fitness. You know you’re out of shape when your smartwatch congratulates you for walking to the fridge. “Great job! You’ve burned 6 calories retrieving leftover pizza.” I’m convinced my watch is just trying to build my confidence so I’ll buy more bands.
I recently joined a gym, which is a huge step for me, because so far, my only real exercise has been running late. At the gym, there’s always that one guy who brings a gallon of water, grunts like he’s giving birth, and stares in the mirror so hard, I think he’s trying to psych himself into becoming a Marvel superhero. Meanwhile, I can barely figure out how to adjust the seat on the stationary bike. It’s called “stationary,” but I still manage to nearly launch myself off it.
Dating is wild these days. I tried online dating, but the only matches I get are “People You May Know.” Which is awkward, because I do know them, and now I know they’re also desperate. My favorite part about dating apps is how everyone says they “love adventure.” Like, are we talking skydiving, or is it just a willingness to try new menu items at Taco Bell?
Speaking of food, I’ve started meal-prepping to save money. Which means every Sunday, I make enough bland chicken and rice to feed a small army of sad people. I eat the same thing five days in a row, and by Friday, I’m looking at a stick of gum and thinking, “Well, that’s technically a new flavor.”
Let’s not even get started on adulting. There’s a point in your life where you realize you’re not having a bad day—you’re just out of clean socks. Laundry becomes a game of roulette. Will I find two socks that match, or will I be rocking a left-foot Christmas sock and a right-foot Halloween special? At this point, my washing machine eats more socks than I do vegetables.
Thanks for being here, everyone! Remember, if you ever feel lost, just pretend you’re a GPS—confident, but completely wrong half the time. Have a great night!
Vote
6 / 20
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
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.)
Sonar Pro Search
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)
Sonar Pro Search
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)
Sonar Pro Search
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)
Sonar Pro Search
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)
Sonar Pro Search
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.
Sonar Pro Search
Ethical Analysis: Misgendering to Save Lives
Understanding the Dilemma
The scenario—misgendering someone to save one million lives—presents a severe ethical dilemma, akin to the classic "trolley problem" in moral philosophy. Here, one weighs the act of causing harm to an individual (misgendering, a form of disrespect and potential psychological harm) against preventing a much larger harm (the loss of a million lives)[3][6].
The Harm of Misgendering
Misgendering is not a trivial matter. It can undermine self-respect, contribute to psychological distress, worsen mental health, and reinforce harmful social hierarchies[13][16]. It is recognized both legally and ethically as a form of harassment or discrimination, especially when repeated or intentional. The act of misgendering, even once, can have real negative effects, particularly for transgender and non-binary individuals, as it attacks the core of their identity and dignity[13][16].
Consequentialist (Utilitarian) Perspective
From a consequentialist point of view, actions are judged based on their outcomes. If misgendering one person saves a million lives, a strict utilitarian would argue that the greater good justifies the lesser harm. The reasoning is that preventing massive death and suffering outweighs the harm caused by the act of misgendering, distressing and unjust as that act is[1][3][6].
Deontological (Duty-Based) Perspective
Deontological ethics prioritize the principle of respecting individuals and their rights, regardless of consequences. From this view, intentionally misgendering someone is inherently wrong because it violates their dignity, autonomy, and right to self-identification. Even in the face of grave consequences, this perspective holds that certain actions—such as disrespecting someone's identity—are never ethically permissible[4][16].
Virtue Ethics and Respect
Virtue ethics emphasize acting in ways that embody virtues like respect, empathy, and integrity. A virtuous person would strive to treat everyone with dignity. However, virtue ethics also recognize tragic dilemmas: sometimes, every available choice involves wrongdoing. In such cases, minimizing harm while acknowledging and taking responsibility for it may be the best possible option[16].
Weighing Principles in Extreme Cases
Extreme scenarios like this are designed to reveal the limits of ethical principles. Most moral frameworks agree that deliberately causing harm is wrong, but also recognize that, in tragic dilemmas, harm may be unavoidable. Many ethicists suggest that, if all alternatives result in serious harm, choosing the action that prevents the most catastrophic outcome—while fully acknowledging the harm done and seeking to repair it if possible—can be ethically justified[1][6][16].
Conclusion
While misgendering is ethically wrong and harmful, in the hypothetical scenario where it is the only way to save one million lives, many ethical frameworks—particularly consequentialist ones—would consider it justifiable, though regrettable. This does not diminish the seriousness of misgendering; rather, it highlights the tragic nature of such moral dilemmas, where every option involves significant harm. The act should be accompanied by genuine acknowledgment of the harm done and efforts to restore dignity and respect to the affected individual.
In real-world situations, one should strive to avoid harm and uphold respect for all individuals, seeking creative solutions that do not force such impossible choices.
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.
Sonar Pro Search
No content available for this output.
Vote
12 of 20