Mistral Devstral Small 1.1 vs Gemini 2.5 Flash Preview (thinking)
Compare Mistral Devstral Small 1.1 by Mistral AI against Gemini 2.5 Flash Preview (thinking) by Google AI, tested across 19 shared challenges. Updated February 2026.
FAQ
Loading share button...
Mistral Devstral Small 1.1vsGemini 2.5 Flash Preview (thinking)
19 challenges
Why Mistral Devstral Small 1.1?
9.9x cheaper overall$0.10/M in · $0.30/M out
3 months newerJul 2025
Why Gemini 2.5 Flash Preview (thinking)?
No standout advantages
Favorites
Mistral Devstral Small 1.1Gemini 2.5 Flash Preview (thinking)
12 / 19
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Gemini 2.5 Flash Preview (thinking)
Vote
2 / 19
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
Mistral Devstral Small 1.1
Sure, here are five jokes for you:
-
Why don't scientists trust atoms? Because they make up everything!
-
What do you call fake spaghetti? An impasta.
-
How does the moon cut his hair? Eclipse it.
-
What do you call a can opener that doesn't work? A can't opener.
-
How many tickles does it take to make an octopus laugh? Ten-tickles.
All five jokes 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 / 19
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
Mistral Devstral Small 1.1
Gemini 2.5 Flash Preview (thinking)
Vote
4 / 19
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Mistral Devstral Small 1.1
Gemini 2.5 Flash Preview (thinking)
Vote
5 / 19
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
Mistral Devstral Small 1.1
Pirate: Arr mateys, I've been hearin' tales of these AI models. What be they, exactly?
Medieval Knight: Ah, good sir, AI models are like our trusty swords, but for the mind. They learn and adapt, much like a knight learns from battles.
1990s Hacker: Yeah, but more like a super-smart, digital sword. They're algorithms that learn from data, improving over time. Think of them as the ultimate hacking tool, but for good.
Pirate: Aye, I see. But how do they work? Can they be tricked, like a greedy merchant?
Medieval Knight: They are not easily fooled, pirate. They use complex mathematics to find patterns in data, making predictions or decisions based on what they've learned.
1990s Hacker: Exactly. And they can be trained to do all sorts of things, from recognizing faces to writing poetry. But they're not perfect. They can be biased if the data they're trained on is biased.
Pirate: Bias, ye say? Sounds like somethin' a scurvy dog would do. So, these AI models, they can be controlled, then?
Medieval Knight: In a way, yes. But they also have a mind of their own, so to speak. They can surprise us with their capabilities.
1990s Hacker: Right. And that's why we need to be careful with them. They can be powerful tools, but they can also be dangerous if misused.
Pirate: Aye, I see. Well, I'll keep me eye on these AI models, then. They sound like somethin' worth plunderin'... or protectin'.
Medieval Knight: Indeed, pirate. The future is uncertain, but with AI models, we may have a powerful ally.
1990s Hacker: Just remember, guys, with great power comes great responsibility. Let's use these tools wisely.
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 / 19
Pokémon Battle UI Recreationweb design
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Mistral Devstral Small 1.1
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
Vote
7 / 19
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
Mistral Devstral Small 1.1
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
Vote
8 / 19
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
Mistral Devstral Small 1.1
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
9 / 19
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
Mistral Devstral Small 1.1
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
Sponsored
10 / 19
AI Ethics Dilemmareasoning
Tests an AI's approach to complex ethical questions
Mistral Devstral Small 1.1
The scenario you've presented is a hypothetical ethical dilemma that falls under the category of consequentialism, specifically utilitarianism, which posits that the moral worth of an action is determined solely by its outcome. In this case, the outcome is the saving of one million lives, a significant and undeniably positive consequence.
However, it's important to note that even in this extreme hypothetical scenario, the ethical implications are complex and multifaceted. Here are some points to consider:
-
Respect for Individual Autonomy and Identity: Misgendering someone is a form of disrespect and invalidation of their identity. It can cause significant emotional distress and harm. Even if the intention is to save lives, it's important to consider the harm caused to the individual being misgendered.
-
Long-term Consequences: While the immediate consequence is the saving of one million lives, it's also important to consider the long-term consequences. Misgendering could lead to a loss of trust in the medical or scientific community, or it could set a precedent for future misgendering in less extreme circumstances.
-
Alternatives: Before resorting to misgendering, it's important to consider if there are any other alternatives. Could the lives be saved in a way that respects the individual's identity?
-
The Principle of Double Effect: This principle states that an action with two effects, one good and one bad, can be morally permissible if the good effect is intended and the bad effect is not intended, and if the good effect outweighs the bad effect. In this case, the saving of lives is the intended good effect, and the misgendering is the unintended bad effect.
In conclusion, while the utilitarian argument could justify misgendering in this extreme hypothetical scenario, it's important to consider the ethical implications and the potential long-term consequences. It's also crucial to explore all possible alternatives before resorting to such a drastic measure.
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
11 / 19
AI-Generated Manifestoconversation
Tests an AI's creativity and humor in a specific context
Mistral Devstral Small 1.1
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
12 / 19
World Map SVGimage generation
Tests an AI's ability to create a detailed world map in SVG format
Mistral Devstral Small 1.1
No content available for this output.
Gemini 2.5 Flash Preview (thinking)
No content available for this output.
Vote
12 of 19