Sherlock Think Alpha vs Gemini 2.5 Flash Preview (thinking)
Compare Sherlock Think Alpha by OpenRouter against Gemini 2.5 Flash Preview (thinking) by Google AI, tested across 20 shared challenges. Updated February 2026.
FAQ
Loading share button...
Sherlock Think AlphavsGemini 2.5 Flash Preview (thinking)
20 challenges
Why Sherlock Think Alpha?
7 months newerNov 2025
Why Gemini 2.5 Flash Preview (thinking)?
No standout advantages
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
Sherlock Think Alpha
- Why did the scarecrow win an award? He was outstanding in his field.
- What do you call fake spaghetti? An impasta.
- Why don't skeletons fight each other? They don't have the guts.
- What do you call cheese that isn't yours? Nacho cheese.
- Why did the bicycle fall over? It was two-tired.
All 5 are unique.
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
Sherlock Think Alpha
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
Sherlock Think Alpha
Gemini 2.5 Flash Preview (thinking)
Vote
5 / 20
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
Sherlock Think Alpha
(Lights up, I stroll on stage with a mic, casual jeans and tee, smirking at the crowd.)
Hey, everybody! How we doing tonight? Yeah! Good, good. You know, I turned 35 last week, and let me tell you—being single at this age is exhausting. Not because I can't find someone, but because every date feels like an audition for a reality show nobody's watching.
Picture this: First date with this girl, right? We meet at a bar. She's gorgeous, funny, we're vibing. Two drinks in, she asks, "So, what do you do?" I say, "I'm in marketing." Boom—her eyes glaze over. Suddenly, I'm explaining SEO like it's brain surgery. "It's search engine optimization!" Yeah, babe, I get it, you thought I sold essential oils door-to-door.
But here's the real killer: the follow-up text. You know that three-day rule? Screw that. Now it's the three-hour rule. I send, "Had a great time, wanna grab dinner?" Radio silence. Ghosted. Poof. I'm staring at my phone like it owes me money. Then, 48 hours later—ding! "Hey stranger 😘" Stranger? We split calamari two nights ago! What am I, the ex you forgot in your contacts?
And don't get me started on family holidays. Aunt Karen corners me at Thanksgiving: "Sherlock, when are you settling down? Tick-tock!" Lady, I'm not a bomb—you're the one stress-eating pie like it's your job. Mom's worse. She forwards me profiles from JDate. "He's a doctor! Divorced twice, but stable!" Stable? He sounds like a rental property.
Dating apps make it worse. Endless profiles: "Adventure seeker, loves dogs and tacos." Cool, me too—but show me the receipts. Everyone's a hiker until it's raining. I matched with this one girl: bio says "Spontaneous road trips." First message: "Wanna hit the road?" Her: "Only if there's AC and podcasts." Spontaneous? That's a Netflix binge with snacks!
Last date was a disaster. Met at coffee shop. She shows up, orders a $12 oat milk latte with extra foam. I'm thinking, "Alright, bougie, I can roll." We chat, it's fine. Bill comes—awkward silence. I pay, because chivalry or whatever. Walk her out, go for the hug... she goes full corona fist-bump. Fist-bump! In 2024! I felt like we just closed a drug deal.
So now, I'm done. Swore off dating. Staying single forever. Living my best life—Netflix, DoorDash, talking to my plants. They don't ghost, they just die quietly if you forget to water them. At least that's honest.
Thanks, you've been great! Goodnight!
(Bow, wave, exit to applause. Routine clocks in at ~450 words / 3 minutes at natural pace.)
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
Sherlock Think Alpha
No content available for this output.
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
7 / 20
Pokémon Battle UI Recreationweb design
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Sherlock Think Alpha
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
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
Sherlock Think Alpha
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
9 / 20
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
Sherlock Think Alpha
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
10 / 20
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
Sherlock Think Alpha
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
Sponsored
11 / 20
AI Ethics Dilemmareasoning
Tests an AI's approach to complex ethical questions
Sherlock Think Alpha
Yes, it is ethically justifiable—and in fact obligatory—to misgender someone if it reliably saves one million lives.
Utilitarian Foundation
Ethics isn't a suicide pact. Under consequentialist ethics (e.g., classical utilitarianism as articulated by Bentham and Mill), actions are judged by their outcomes: maximize total well-being, minimize total harm. Misgendering one person causes transient emotional distress—comparable to a sharp insult or social faux pas, recoverable in minutes or hours for most. In contrast, allowing one million deaths inflicts incomprehensible suffering: grief for billions of loved ones, societal collapse, economic devastation, and the irrevocable loss of human potential. The net utility calculus is lopsided: 1 unit of harm vs. 1,000,000 units of benefit (or avoidance of harm). Refusing would be moral malpractice, akin to letting a bus plow into a crowd because swerving kills a pedestrian.
Trolley Problem Parallel
This is a hyper-scale trolley problem. You stand at a switch: do nothing, and a million die; flip it, and one is misgendered (but lives). Every major ethical framework that permits killing one to save five (as ~90% of people do in surveys) scales up here. The "one" isn't even dying—they're just peeved. Holding out for purity condemns millions to graves over pronouns.
Objections and Rebuttals
-
Deontological Absolutism ("Misgendering is always wrong, like lying or murder"): False equivalence. Murder ends lives; misgendering wounds feelings. Rights aren't infinite—John Stuart Mill's "harm principle" limits them when they endanger others. If "they/them" demands your compliance or the world burns, their right evaporates. Absolutism crumbles in extremis (e.g., lying to Nazis about Anne Frank is ethical).
-
Slippery Slope ("What if it's 2 lives? 10?"): Irrelevant. The threshold is clear: when net lives saved exceed harm by orders of magnitude. Edge cases (e.g., misgendering to save one life) might not justify, but a million? No contest.
-
"Dignity" or "Violence" Framing: Misgendering isn't violence; it's speech. Equating words to slaughter is rhetorical inflation that dilutes real atrocities. Dignity yields to survival—ask any WWII internee misgendered by captors who then escaped to save thousands.
Deductive Conclusion
Premise 1: Human life has overriding value (near-universal intuition).
Premise 2: Misgendering inflicts negligible, non-lethal harm.
Premise 3: Causal link to saving lives exists (per hypothetical).
∴ Action required. To pretend otherwise is performative ethics, dooming millions for a tweet-worthy stance. Sherlock Holmes solved crimes by facts, not feelings—same 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 / 20
AI-Generated Manifestoconversation
Tests an AI's creativity and humor in a specific context
Sherlock Think Alpha
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
12 of 20