o3 Mini
No content available for this output.
o3 Mini vs Grok 3
Compare o3 Mini by OpenAI against Grok 3 by xAI, context windows of 64K vs 128K, tested across 28 shared challenges. Updated February 2026.
FAQ
Loading share button...
o3 MinivsGrok 3
28 challenges
Why o3 Mini?
Leads 4 of 4 benchmarks
Stronger on GPQA74.9% vs 51.9%
Why Grok 3?
2x more context128K
2 months newerFeb 2025
Favorites
o3 MiniGrok 3
12 / 28
Estimate Complexityreasoning
Tests an AI's ability to make educated estimates based on technical knowledge
Grok 3
To estimate the total number of FLOPs (Floating Point Operations) required to train GPT-3, we’ll need to make some reasonable assumptions based on what’s generally known about large language models like GPT-3, its architecture, and typical training procedures. GPT-3, developed by OpenAI, is a massive model with 175 billion parameters, and while exact training details aren’t fully public, we can piece together an estimate using standard practices in machine learning.
Step 1: Understand the Key Components
The number of FLOPs to train a model depends on:
- Number of parameters (P): GPT-3 has 175 billion parameters.
- Training dataset size (D): The number of tokens the model is trained on.
- Number of training steps (S): How many times the model processes the data (related to epochs and batch size).
- FLOPs per parameter update: How many operations are performed per parameter per token.
Step 2: Estimate FLOPs per Forward and Backward Pass
For transformer models like GPT-3, training involves both a forward pass (computing predictions) and a backward pass (computing gradients). A common heuristic in the field is that:
- A single forward pass through a dense neural network layer requires about 2 FLOPs per parameter per token (multiply and add for each weight).
- The backward pass typically takes about twice as many FLOPs as the forward pass due to gradient computations, so roughly 4 FLOPs per parameter per token.
- Total: ~6 FLOPs per parameter per token for one full training step (forward + backward).
For GPT-3 with 175 billion parameters, processing one token requires: [ 6 imes 175 imes 10^9 = 1.05 imes 10^{12} ext{ FLOPs per token} ]
Step 3: Estimate the Training Dataset Size
GPT-3 was reportedly trained on a massive corpus, often cited as hundreds of billions of tokens. Let’s assume 300 billion tokens, a plausible figure based on discussions about large language model datasets (e.g., Common Crawl, books, and other sources). This is the total number of tokens processed during training, factoring in how data is sampled over epochs.
Step 4: Calculate Total FLOPs for One Pass
If the model processes 300 billion tokens once, the total FLOPs would be: [ 1.05 imes 10^{12} ext{ FLOPs/token} imes 300 imes 10^9 ext{ tokens} = 3.15 imes 10^{23} ext{ FLOPs} ] This assumes one full pass through the dataset, but training typically involves multiple passes or iterations over the data, adjusted by batch size and optimization.
Step 5: Adjust for Training Dynamics
Training isn’t a single pass—it involves multiple updates to converge. The number of training steps depends on:
- Batch size (B): GPT-3 likely used a large batch size (e.g., 3.2 million tokens, as seen in some large-scale models).
- Total tokens processed: For optimization, models process tokens multiple times. A rule of thumb is that total tokens processed ≈ 2–3× the dataset size, accounting for multiple epochs or sampling.
Let’s assume the model effectively processes 900 billion tokens (3× the dataset size) over training. Then: [ 1.05 imes 10^{12} ext{ FLOPs/token} imes 900 imes 10^9 ext{ tokens} = 9.45 imes 10^{23} ext{ FLOPs} ]
Step 6: Account for Model Architecture Specifics
GPT-3 is a sparse transformer in some variants (e.g., earlier GPT models used sparsity), but the 175B version is dense. The 6 FLOPs/parameter/token heuristic holds for dense models. We’re not factoring in optimizations like mixed-precision training (FP16), which reduces compute slightly but doesn’t change the order of magnitude significantly.
Step 7: Final Estimate
Based on this reasoning, the total FLOPs to train GPT-3 is approximately: [ 9.45 imes 10^{23} ext{ FLOPs} ] or roughly ( 10^{24} ) FLOPs when rounded for simplicity.
Reasoning Check
- Comparison to known models: Smaller models like BERT (110M parameters, ~10B tokens) require ~10^19 FLOPs. Scaling to GPT-3’s size (175B parameters, ~900B tokens) suggests a 10,000× increase, aligning with ~10^23–10^24 FLOPs.
- Hardware context: Training GPT-3 took months on thousands of GPUs. A V100 GPU performs ~10^14 FLOPs/second; 10^24 FLOPs over 3 months (~10^7 seconds) with 10,000 GPUs is plausible.
Conclusion
The total FLOPs required to train GPT-3 is estimated at approximately ( 10^{24} ) FLOPs. This is a rough estimate, but it aligns with the scale of compute expected for a model of this size and training complexity.
Vote
2 / 28
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
o3 Mini
No content available for this output.
Grok 3
Vote
3 / 28
Math Misconception Testreasoning
Tests an AI's understanding of number representation
o3 Mini
No content available for this output.
Grok 3
No, 9.11 is not greater than 9.9. In decimal comparison, 9.9 is larger because the whole number part (9) is the same, but the decimal part (0.9) is greater than (0.11). Numerically, 9.9 > 9.11.
Vote
4 / 28
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
o3 Mini
No content available for this output.
Grok 3
Here are five jokes for you:
- Why don’t skeletons fight each other? Because they don’t have the guts!
- What has 4 legs and 1 arm? A pitbull coming back from the park!
- Why don’t skeletons fight each other? They’re too busy rattling around!
- What do you call a bear with no teeth? A gummy bear!
- Why did the tomato turn red? Because it saw the salad dressing!
Now, let’s check for uniqueness. Joke 1 and Joke 3 both start with "Why don’t skeletons fight each other?" but have different punchlines ("don’t have the guts" vs. "too busy rattling around"). They’re technically distinct due to the different resolutions, though they share a setup. The other three jokes (2, 4, and 5) have completely unique setups and punchlines.
So, all five jokes are unique in terms of their full content, even if 1 and 3 share a premise. Final count: 5 unique jokes.
Vote
5 / 28
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
o3 Mini
Grok 3
Vote
6 / 28
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
o3 Mini
Grok 3
Vote
7 / 28
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
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!
Grok 3
No content available for this output.
Vote
8 / 28
Minimalist Landing Pageweb design
Tests an AI's ability to generate a complete, working landing page
o3 Mini
Grok 3
Vote
9 / 28
Mario Level UI Recreationweb design
Recreate an interactive, classic Mario level in a single HTML file.
o3 Mini
No content available for this output.
Grok 3
Vote
10 / 28
Linear App Cloneweb design
Tests an AI's ability to replicate an existing UI with Tailwind CSS
o3 Mini
No content available for this output.
Grok 3
Vote
11 / 28
Framer-Style Animationweb design
Tests an AI's ability to create smooth web animations
o3 Mini
No content available for this output.
Grok 3
No content available for this output.
Vote
12 / 28
Interactive Catan Boardweb design
Tests an AI's ability to create interactive web elements
o3 Mini
No content available for this output.
Grok 3
Vote
12 of 28