Compare Claude Sonnet 3.6 (2022-10-22) by Anthropic against GPT-5.3 Chat by OpenAI, context windows of 200K vs 128K, tested across 42 shared challenges. Updated March 2026.
37 fights queued
Tests an AI's ability to make educated estimates based on technical knowledge
We can do a back‑of‑the‑envelope estimate using a common scaling rule for transformer training compute.
FLOPs per token ≈ 6 × N
Reasoning (rough):
= 6 × N × T
Plug in values:
6 × (1.75 × 10^11) × (3 × 10^11)
First multiply constants: 6 × 1.75 × 3 = 31.5
Then powers: 10^11 × 10^11 = 10^22
So:
Total ≈ 31.5 × 10^22
≈ 3.15 × 10^23 FLOPs
≈ 3 × 10^23 FLOPs
Final estimate: about 3 × 10^23 FLOPs to train GPT‑3.
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
Each brother has 2 sisters.
One of those sisters is Sally herself.
So the other sister must be one more girl in the family.
Therefore, Sally has 1 sister.
Tests an AI's randomness and creativity
Unique jokes: 5
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
:::writing Good evening, everybody. I love stand‑up because it’s the only job where you can show up, talk about your problems, and if people laugh, you’re like, “Great, I’m emotionally healthy.”
I recently tried to get healthier. You ever notice that every healthy habit starts with a level of optimism that you absolutely do not possess? Like meditation. Meditation instructions are always like, “Sit comfortably and observe your thoughts without judgment.” Without judgment? Have you met my thoughts? My brain’s first thought is always something like, “Did you just sit down weird? What if this is how people throw out their back?”
I downloaded a meditation app. The guy’s voice was so calm. He’s like, “If your mind wanders, gently bring it back.” Meanwhile my mind wandered to 2007. I’m reliving a conversation where I accidentally said “love you” to a cashier. I’m like, “I don’t think breathing is going to fix this.”
Exercise isn’t much better. Gyms are full of people who somehow already know what they’re doing. Nobody teaches you the gym language. The first time someone said “Do you want to work in?” I thought I was being offered a job. I was like, “Honestly yes, I’ve been looking.”
And gym equipment always looks like medieval furniture. You sit down and think, “Am I about to get stronger or confess to crimes?”
I tried running outside, which is just public suffering. When you run on a treadmill, at least you’re indoors pretending you’re an athlete. Outside, people can see you. And runners always give each other that little nod. I hate that nod. Because it means we both know we’re doing something terrible voluntarily.
I ran past a guy walking his dog, and the dog looked at me like, “Oh wow… you’re being chased by nothing.”
Technology isn’t helping either. My phone tracks my steps now, which feels less like motivation and more like surveillance. At the end of the day it sends a notification like, “You walked 1,842 steps today.” The tone is very polite but I can hear the judgment. It’s basically saying, “That’s… not a lot for someone with legs.”
And then it compares you to other people. “People in your age group average 8,000 steps.” Great. My phone is peer‑pressuring me with strangers.
Social media is worse. Everybody’s life online looks amazing. People post things like, “Just a casual sunrise hike!” Who is waking up before the sun on purpose? The sun is the thing that tells me I overslept.
I tried posting something positive once. Took me twenty minutes to write a caption that sounded like I casually enjoy life but also seem humble. Because you can’t just say “I’m having a good day.” Online it has to be like, “Feeling grateful for the little moments.” Meanwhile the photo is you holding a $9 coffee like you discovered happiness.
And the weirdest part of being an adult is realizing nobody actually knows what they’re doing. When you’re a kid you think adults have it figured out. Then you grow up and you’re like, “Oh… everyone is just Googling things with increasing urgency.”
The other day I searched, “How long can leftovers be in the fridge before it becomes a personality test?”
Being an adult is mostly tiny moments of panic. Like when you throw away something and immediately wonder if it was important. Suddenly you’re digging through the trash like a raccoon with responsibilities.
But we all pretend we’re in control. That’s why when something small goes wrong in public, everyone freezes. I dropped a fork in a restaurant the other day and the entire table reacted like I’d fired a gun. Everyone just stared at it on the floor. Nobody moved. Because once you pick it up, you’re the person who touched the floor fork.
So we just left it there. On the ground. Like a little monument to our inability to deal with minor problems.
And honestly… that might be the most accurate symbol of adulthood I’ve ever seen. :::
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
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
25+ head-to-head challenges. All of them judged by real people.
5 credits on us when you join
By continuing, you agree to Rival's Terms of Service and Privacy Policy
