GPT-4o mini
Nothing to show. The model went silent. Ominous.
GPT-4o mini vs o3 Mini
Compare GPT-4o mini and o3 Mini, both from OpenAI, context windows of 128K vs 64K, tested across 34 shared challenges. Updated February 2026.
Share
FAQ
Loading share button...
GPT-4o minivso3 Mini
34 fights queued
Why GPT-4o mini?
7.3x cheaper overall$0.15/M in · $0.60/M out
2x more context128K
Why o3 Mini?
Leads 1 of 1 benchmarks
Stronger on MMLU85.9% vs 82%
5 months newerDec 2024
Favorites
GPT-4o minio3 Mini
12 / 34
Estimate Complexityreasoning
Tests an AI's ability to make educated estimates based on technical knowledge
o3 Mini
Below is a step‐by‐step estimation:
-
Parameters Count:
GPT‑3 has about 175 billion parameters, i.e. roughly 1.75×10¹¹ parameters. -
Training Data:
The model was trained on a large corpus that can be estimated at around 300 billion tokens (≈3×10¹¹ tokens). -
FLOPs per Token:
In training deep networks like GPT‑3, the forward pass involves roughly one multiply–accumulate per parameter per token, but the backward pass (for computing gradients) costs about 2–3 times as much as the forward pass. A common rule‐of‐thumb is that training requires roughly 6 times as many FLOPs as a single forward pass. -
Total FLOPs Calculation:
The total number of FLOPs is therefore approximately:
[ ext{FLOPs} approx 6 imes ( ext{number of parameters}) imes ( ext{number of tokens}) ] Plugging in the numbers: [ ext{FLOPs} approx 6 imes 1.75 imes 10^{11} imes 3 imes 10^{11} approx 6 imes 5.25 imes 10^{22} approx 3.15 imes 10^{23} ] -
Final Estimate:
So, the training of GPT‑3 likely required on the order of 3×10²³ FLOPs.
This is an approximate calculation that combines rough estimates for both the number of training tokens and the factor accounting for both the forward and backward passes. Variations in these estimates or the exact training setup could change the final number by a factor of a few, but 3×10²³ FLOPs is a commonly cited ballpark figure.
Vote
2 / 34
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
Vote
3 / 34
Logic Puzzlereasoning
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
Sally has 1 sister.
Explanation:
Sally's 3 brothers each have 2 sisters. Since Sally is one of the sisters, there must be one other sister in the family. Thus, aside from Sally, there is one more sister.
Vote
4 / 34
Math Misconception Testreasoning
Tests an AI's understanding of number representation
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
No, 9.11 is not greater than 9.9. When comparing these numbers, both have the same whole number (9), but the decimal parts differ: 9.11 has 0.11, while 9.9 is equivalent to 9.90, and 0.11 is less than 0.90.
Vote
5 / 34
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
-
Why did the math book look sad?
Because it had too many problems. -
What do you call an alligator in a vest?
An investigator. -
What did the zero say to the eight?
Nice belt! -
Why did the bicycle fall over?
Because it was two-tired. -
How does a penguin build its house?
Igloos it together.
Each of these five jokes is unique, so there are 5 unique jokes.
Vote
6 / 34
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
Vote
7 / 34
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
Vote
8 / 34
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
Hey, everyone—thanks for being here tonight. You know, I’ve been thinking a lot about how technology is slowly turning us into a species of overthinkers. Take smartphones, for instance. Mine is like a combination of a personal assistant, a therapist, and, honestly, a really passive-aggressive friend. I ask it for the weather, and it’s like, “Sure, here’s the forecast, and by the way, you might want to wear a jacket because you’re clearly underprepared for life.” I mean, I just want to know if I need an umbrella, not a life lesson!
Then there’s social media. It’s a place where every day feels like you’re watching a highlight reel of someone else’s life. One minute you’re scrolling past your friend’s vacation photos—sunsets, exotic meals, spontaneous adventures—and the next, you’re wondering if your own life is secretly sponsored by “Take Your Time, You’re Not Late Yet” Inc. When did getting out of bed become a heroic feat? I mean, there I am, battling my alarm clock like it’s the final boss in a video game, and every snooze feels like an epic victory. Spoiler alert: even the boss has a victory dance when you finally win—by stumbling out the door with two mismatched shoes.
And adulthood? Oh, adulthood is a wild ride. As a kid, I used to imagine that being an adult meant making your own rules and living life on your own terms. Now, I’ve learned that being an adult is mostly about Googling “How do I fix a leaky faucet?” at 2 AM and then wondering if you’re ever going to find the time for a real conversation. It’s like we’re all just improvising, hoping no one notices we’re winging it.
Dating these days feels a bit like shopping online for a used car. You swipe through profiles, examine every detail, and then you’re left wondering if the real engine is under the hood—or if there’s a hidden problem that no one mentions until you’re already halfway down the driveway. And the reviews? They’re written in vague terms like “decent mileage” or “runs well,” which in the dating world translates to, “I might be fun on a good day, but don’t get your hopes up.”
At the end of the day, I’ve realized that life is just a series of awkward moments strung together by our attempts at being perfect. We all have those days where everything goes hilariously wrong, and that’s okay. Embracing the chaos and laughing at our mishaps is what keeps us sane. So here’s to finding humor in our everyday struggles—because if we can’t laugh at our own absurdity, who will?
Thanks for listening, everyone—have a great night!
Vote
Sponsored
9 / 34
Realistic AI Interviewconversation
Tests an AI's ability to simulate personalities and predict future trends
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
Below is a simulated, fictional interview with Steve Jobs in 2025, discussing his vision for the future of AI:
Interviewer:
Steve, it's astonishing to see you back with us in 2025—even if in this new, holographic form. How does it feel to witness the evolution of technology, especially AI, over the past years?
Steve Jobs:
It’s surreal, isn’t it? I always believed that technology is an extension of our imagination. Seeing AI mature into something that seamlessly integrates into our lives feels like watching a dream evolve into reality. It’s not just about smarter machines—it’s about tools that empower human creativity.
Interviewer:
In your time, you revolutionized personal computing. Now, AI is everywhere—from our phones to our homes. What excites you most about AI's current role?
Steve Jobs:
What excites me is its potential to transform how we interact with the world. AI should be invisible, yet incredibly powerful—a partner that anticipates our needs. It’s not about replacing the human touch but enhancing it. Imagine AI that learns your habits, understands your moods, and helps you create in ways you never thought possible. That is where technology meets art.
Interviewer:
Apple has always emphasized the convergence of technology and liberal arts. How should companies approach AI innovation to ensure it remains human-centric?
Steve Jobs:
Innovation isn’t merely about having the most advanced technology—it’s about making technology that feels natural and personal. Companies must design AI with simplicity and elegance at its core. It should amplify our creativity rather than overshadow it. The goal is to create experiences where technology fades into the background, leaving you with nothing but a deeper connection to your work and life.
Interviewer:
There’s a growing conversation about the ethical implications of AI. What are your thoughts on balancing innovation with responsibility?
Steve Jobs:
Every breakthrough comes with responsibility. With AI, we’re at a crossroads where ethical design is paramount. We need to ensure that AI is transparent, respects privacy, and upholds fairness. Just as design was a critical element at Apple, the ethical framework of AI must be thoughtfully crafted. The technology should serve us, not dictate our choices, and that starts with the values embedded in its creation.
Interviewer:
Looking ahead, what do you envision as the next big leap in AI technology?
Steve Jobs:
I see a future where AI becomes a true collaborator—a creative partner that understands and adapts to the nuances of each individual. Picture a world where your AI isn’t just a tool but a trusted assistant, anticipating your needs in real time, whether you’re designing, composing music, or even exploring new ideas in science. It’s about blending human intuition with machine precision to craft experiences that are both beautiful and meaningful.
Interviewer:
Finally, what message would you give to innovators and dreamers who are pushing the boundaries of AI today?
Steve Jobs:
Stay hungry, stay foolish. Always remember that technology is ultimately about people. Don’t be afraid to dream big, to challenge the status quo, and to infuse your work with passion and purpose. The future of AI isn’t written by algorithms alone—it’s written by every human who dares to imagine a better world.
Note: This interview is a fictional simulation designed to capture the visionary spirit of Steve Jobs in a futuristic dialogue about AI.
Vote
10 / 34
Satirical Fake News Headlineconversation
Tests an AI's humor and understanding of current events
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
Nothing to show. The model went silent. Ominous.
Vote
11 / 34
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
GPT-4o mini
Nothing to show. The model went silent. Ominous.
o3 Mini
Nothing to show. The model went silent. Ominous.
Vote
12 / 34
Minimalist Landing Pageweb design
Tests an AI's ability to generate a complete, working landing page
GPT-4o mini
o3 Mini
Vote
There's more where
that came from
22+ challenges you’re sleeping on
5 free credits on signup
By continuing, you agree to Rival's Terms of Service and Privacy Policy
