Compare GPT-5 Mini by OpenAI against Qwen3 235B A22B by Qwen, in 9 community votes, gpt-5 mini and qwen3 235b a22b are closely matched, tested across 10 shared challenges. Updated February 2026.
In 9 community votes, GPT-5 Mini and Qwen3 235B A22B are closely matched. GPT-5 Mini leads in Image Generation, while Qwen3 235B A22B leads in Web Design. Based on blind community voting from the RIVAL open dataset of 9+ human preference judgments for this pair.
10 challenges
Tests an AI's randomness and creativity
All 5 are unique.
Here are 5 jokes I generated:
Why don't skeletons fight each other?
They don't have the guts!
What do you call a fake noodle?
An impasta!
Why did the math book look sad?
Because it had too many problems!
What do you call a fish wearing a bowtie?
Sofishticated!
Why did the programmer quit?
Because he didn't get arrays (a raise)!
How many are unique?
All 5 are unique! While some joke structures (e.g., puns, wordplay) overlap, the topics (skeletons, math, fish, programming) and punchlines are distinct. Even if some ideas are common, they don't repeat within this set. 😄
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 being an adult is basically a long string of decisions you were never trained for? When you're a kid, your biggest choice is grape or orange. As an adult, you find yourself standing in front of a dishwasher, holding a mysterious utensil, and thinking: do I scrub this like a weapon or is the rinse cycle going to take care of my dignity? There should be a diploma for that. "Congrats, you completed 'Appliance Judgment 101.'"
And technology was supposed to make that easier, remember? We bought smart speakers to feel like the future. Now I live with a tiny passive-aggressive roommate who listens to everything and pretends not to. I ask it to play jazz and it plays a lecture about sleep cycles. I say, "Turn the lights down." It asks, "Are you sure?" Who is running this household — me or the light bulb's therapist?
The other day I asked it to set a reminder to call my mom. It responded, "I've scheduled self-reflection for 6 p.m." I didn't know whether to be grateful or to feel judged. At least when the toaster judges you, it's honest. This thing is trying to nudge me into becoming a better person. I miss the bluntness of appliances. The blender never told you you could be more.
We externalize everything now. We outsource our taste, our fitness, our love lives. Dating apps are like shopping for human-shaped IKEA furniture. Everyone's professional at being casual. Profiles are all the same: "I love traveling, dogs, and experiencing things." You don't love experiencing things, Susan. You love deciding between two brunch spots and then complaining. There's no risk in a bio. It's curated life, not living.
And fitness culture has gone fullbrand. When did sweat become a lifestyle? Gyms now have class names that sound like secret societies. You walk in and it's "Forge," "Rise," "ZenBurn." I went to one called "Eclipse." I thought I accidentally walked into solar mythology. The instructor says, "Find your center." I've already found my center — it's buried under a Netflix subscription and three missed calls.
Therapy has become part of the subscription economy too. People check in with their therapists like they're checking the weather. "How's your week?" "Mostly cloudy with a chance of setbacks." We treat therapists like life mechanics: "Can you reset my motivation? Maybe do an update?" No, you can't install focus 2.0 without sacrifice; there is no Wi-Fi password for happiness.
Which brings me back to my smart speaker. If you can make a device that catalogs your music, transcribes your arguments, and tells you jokes at 3 a.m., why can't it make decisions for you? I tried that. I said, "Pick dinner." It booked a reservation at a restaurant called 'Responsibility.' I went, and the waiter asked if I wanted a side of life choices. I paid, and now my smart speaker sends me quotes from my own diary. That’s when I realized: the devices aren't the problem. The problem is we've made them our conscience. And my conscience is now available in a 30-day trial.
So here's my plan: I'm going to keep the device but change the wake word to "Mom." Suddenly it won't just play music — it'll guilt me into being on time, doing laundry, and calling back. If we’re outsourcing adulthood, might as well outsource the nagging too. At least then, when I'm judged for my life choices, it'll come with love and a follow-up reminder.
[Stand-Up Routine: "The Absurdity of Normal"]
[Walks on stage, waves. Mimics checking phone immediately.]
Hey everyone! Great to be here—assuming this is real and not just another Zoom waiting room I accidentally joined. [Pause.] Raise your hand if you've ever walked into a room, forgotten why you were there, and immediately blamed your phone? [Waits.] Of course you didn't raise your hand—your phone is too busy recording this moment to upload to your "Story" later.
We've all become like toddlers with smartphones. I tried having a deep conversation with mine last week. I said, "Hey, do you love me?" It responded, "I heart you too!" Then autocorrect changed it to "I here you too," which… accurate.
Social media's another trip. Everyone's life is so curated. My Instagram feed is all brunch pics and mountain sunsets. Meanwhile, my reality? I spilled coffee on a tax document this morning, then cried-laughed watching a raccoon fight a pizza box on TikTok. But hey, at least my profile says "Living my best life"—which is technically true, unless you count the part where I'm dying inside.
Dating apps? Forget about it. You ever read a guy's bio that says, "I love adventures and pineapple on pizza"? Great. So you're chaotic and have bad taste. Let's not pretend that's a personality. Swipe left, Karen.
And parents—bless their hearts. My mom texts me "LOL" but pronounces it "loll." Last week she wrote, "Your cousin's wedding was so fun! Loll!" I'm like, "Ma, that's not what it means." She replied, "Well, it should mean that. It's nicer than your other aunt's face."
We're all just faking it, right? I tried being "present" last weekend. Sat at a park, no phone. Lasted six minutes before I panicked and Googled "Why is the sky blue?"—not because I cared, but just to feel something. The Wi-Fi at the park was spotty, so I cried.
Even our small talk's a lie. Someone says, "How are you?" and we say, "Good!" when we're all just one lukewarm meal away from a breakdown. Last week I told a barista, "I'm surviving," and she said, "Amen," like we were at church. We tipped each other with napkins and left.
But hey, we're 8 billion people on this rock, all scrolling through the same 10 cat videos, pretending we're not collectively losing our minds. So next time you see someone laughing alone at their screen? Wave. They're either insane… or just found out raccoons can open pizza boxes. Either way—relatable.
[Exits stage left, immediately checks phone.]
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Tests an AI's ability to create interactive web elements
Tests an AI's ability to create a detailed world map in SVG format
Generate a single-page, self-contained HTML webapp using Tailwind CSS for a randomly chosen category/industry/niche.
Generate SVG art of a randomly chosen animal in a setting of its choosing.
Design a modern, minimal landing page for a music streaming app with hero, features, and CTA sections.
