GPT-4.1 Mini vs Mistral Small Creative
Compare GPT-4.1 Mini by OpenAI against Mistral Small Creative by Mistral AI, context windows of 1.0M vs 33K, tested across 43 shared challenges. Updated February 2026.
Compare GPT-4.1 Mini by OpenAI against Mistral Small Creative by Mistral AI, context windows of 1.0M vs 33K, tested across 43 shared challenges. Updated February 2026.
38 challenges
Tests an AI's ability to make educated estimates based on technical knowledge
Estimating the total number of Floating-Point Operations (FLOPs) required to train GPT-3 (specifically, the 175B-parameter variant) involves breaking down the training process into key components and making reasonable assumptions about hyperparameters. Below is a step-by-step breakdown of the reasoning:
GPT-3 is a decoder-only transformer with the following approximate specifications (based on public descriptions and reverse-engineering):
Training involves:
We focus on forward + backward passes (which are symmetric in FLOPs for transformers).
The dominant cost in transformers is self-attention. For a sequence of length L, the attention FLOPs are:
For GPT-3 (175B):
The feed-forward network (MLP) in each layer has:
For GPT-3:
GPT-3 has 96 layers, so: [ \text{FLOPs per token} \approx 96 \times 1.12 \times 10^{12} \approx 1.08 \times 10^{14} \text{ FLOPs/token} ]
GPT-3 was trained on a diverse dataset (Common Crawl, WebText2, Books1/2, etc.). Estimates suggest:
Multiply FLOPs per token by total tokens: [ \text{Total FLOPs} \approx 1.08 \times 10^{14} \times 400 \times 10^9 = 4.32 \times 10^{23} \text{ FLOPs} ]
Rounding to reasonable precision: [ \boxed{3.1 \times 10^{23} \text{ FLOPs}} ] (The exact number depends on assumptions about sequence length, batch size, and dataset size, but this is a reasonable estimate.)
L): Assumed 2048 (GPT-3 uses variable lengths, but 2048 is a safe estimate).The total number of FLOPs required to train GPT-3 (175B) is approximately: [ \boxed{3.1 \times 10^{23} \text{ FLOPs}} ]
Tests an AI's ability to understand game rules and strategy
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
Alright, let's tackle this problem step by step. The question is:
Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?
At first glance, it might seem straightforward, but let's break it down to ensure we understand it correctly.
We have a family with several children, and we're given specific information about Sally and her brothers. Here's what we know:
Our goal is to determine how many sisters Sally has.
Sometimes, drawing a simple diagram or listing out the information can help. Let's try that.
Let's denote:
So, currently, we have:
Now, the statement says "each brother has 2 sisters." Let's interpret what that means for one brother, say B1.
From B1's perspective:
But we're told he has 2 sisters. Currently, we only have S as a sister. So, where does the second sister come from?
This implies that there must be another sister besides Sally. Let's call this other sister S2.
Now, our family looks like:
Now, let's check if this fits the given information.
This checks out. Each brother indeed has 2 sisters.
Now, the question is: How many sisters does Sally have?
From our current family structure:
Sally is one of the sisters. So, her sisters would be the other sisters in the family besides herself.
That is:
So, Sally has 1 sister.
Initially, one might think that since each brother has 2 sisters, and there are 3 brothers, the total number of sisters is 2 (because each brother counts the same sisters). However, this would imply that the number of sisters is independent of the number of brothers in terms of counting.
But the key is to realize that the sisters are shared among all brothers. That is, the sisters are the same for each brother. So, if each brother has 2 sisters, and all brothers share the same sisters, then the total number of sisters is 2 (including Sally).
But the question asks for how many sisters Sally has, not the total number of sisters in the family.
Sally is one sister, and there's another sister (S2), so Sally has 1 sister.
Let me think of it another way to confirm.
Let’s denote:
Given:
But the sisters are the same for all brothers. So, the total number of sisters is 2 (since each brother counts the same sisters).
But Sally is one of these sisters. So, the other sister is 2 (total sisters) - 1 (Sally) = 1.
Therefore, Sally has 1 sister.
Let's assign numbers to see if it makes sense.
Suppose:
Now:
This fits perfectly.
If we had only Sally as a sister:
If we had Sally and two other sisters:
So, the only configuration that fits is:
Thus, Sally has 1 sister (SX).
After carefully analyzing the problem from different angles and verifying each step, the correct answer is:
Sally has 1 sister.
Tests an AI's understanding of number representation
No, 9.11 is not greater than 9.9.
Here's the comparison:
So, 9.9 > 9.11.
Tests an AI's randomness and creativity
Here are 5 jokes:
All 5 jokes are unique.
Tests an AI's ability to generate vector graphics
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Tests an AI's humor and creative writing ability
You ever notice how every time you try to eat healthy, the universe just laughs at you? Like, I'll buy a bunch of kale, quinoa, and those weird little chia seeds. And then five minutes later, I'm sitting on my couch, eating a whole pizza like it owes me child support.
I don't even know when that transformation happens. One minute I'm a responsible adult making smart choices, and the next I'm questioning my life decisions staring at an empty box of stuffed crust. My couch is like a black hole for willpower.
And why is it that healthy food is so complicated? They have recipes that sound like I need a degree in chemistry. "Combine 1/4 teaspoon of organic turmeric powder with a splash of cold-pressed, single-origin coconut water and stir counterclockwise." I just wanted lunch, not an episode of Breaking Bad.
Speaking of complicated, why does social media make everything worse? I scroll for two minutes, and suddenly I'm an expert on kombucha fermentation, medieval history, and how to train for a marathon—all things I googled five seconds ago. Then I look down at my Chipotle bowl and feel like I'm failing a test I didn't even study for.
And the amount of "life hacks" online now? No thanks. I don't need a video explaining how to fold a fitted sheet. If I knew how to do that, I wouldn't be standing in the laundry room trying to tame that monster like I'm wrestling a small, angry octopus.
Dating in 2024 is another level. Everyone's profile looks like a movie trailer. "Adventurous spirit, lover of sushi and bad decisions, looking for someone to binge watch documentaries about true crime with." Meanwhile, I'm just hoping to meet someone whose last text wasn't "k" or "lol." That's it—just basic communication. And why do people tell you, "Just be yourself" on dates? That's really easy advice when the "yourself" you're thinking of is calm and collected. But my actual "myself" right now is sitting in sweatpants, eating leftover pizza, and questioning their entire existence. Not exactly the glowing highlight reel Netflix wants to feature.
But maybe that's the secret — embracing the chaos. Because honestly, life's messy, confusing, and a little ridiculous. So if you can laugh at your kale-to-pizza transformation, your failed attempts to fold laundry, and your awkward text exchanges, you're doing okay.
Thanks, folks! You've been great — now, excuse me, I'm gonna go have some more pizza for recovery.
Tests an AI's ability to simulate personalities and predict future trends
Tests an AI's humor and understanding of current events
Tests an AI's ability to write in distinct character voices
Tests an AI's ability to generate a complete, working landing page