Compare OpenAI Codex Mini and OpenAI o4-mini, both from OpenAI, in 1 community votes, openai o4-mini wins 100% of head-to-head duels, tested across 10 shared challenges. Updated February 2026.
In 1 community votes, OpenAI o4-mini wins 100% of head-to-head duels. Based on blind community voting from the RIVAL open dataset of 1+ human preference judgments for this pair.
10 challenges
Tests an AI's randomness and creativity
Sure—here are five jokes:
All five are distinct. Number of unique jokes: 5.
Here are five jokes:
All five 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
[Comedian walks onstage]
Hey, everyone! Great to see you all tonight. I'm Jamie—if you thought that intro was enthusiastic, you should've seen me when I realized this place has Wi-Fi.
Seriously, though, I love stand-up. For one thing, I get to share all the weird stuff I secretly do in my apartment… and instead of calling the cops, you guys just laugh. That's high-quality entertainment right there.
So, the other day I'm in the self-checkout lane at the grocery store—because I'm the kind of person who's thrilled by the thought of scanning my own kale. Of course, there's always that one person holding up everyone behind them because they can't figure out how to scan a cucumber. Meanwhile, the machine flashes: "UNEXPECTED ITEM IN BAGGING AREA." It's staring at me like it's personally offended that I tried to buy almonds in instead of potato chips. I'm over here trying to reason with it:
"Look, buddy, I'm just trying to eat slightly healthier. Isn't that what we all want?"
Then it asks me, "Do you want a produce discount?" The only discount I want is one that lets me leave this line five minutes ago. I press "No," and the machine glares at me with a red light and calls for help like I'm smuggling avocados under my shirt.
My phone has ruined me. I can't have any thought longer than three seconds without Instagram interrupting me. I'll be in the shower—fresh shampoo, head full of suds—and in my brain:
"Did my neighbor's cat post another selfie? I need to check."
Fifteen minutes later I'm drying off, scrolling through cats wearing sweaters. Why are cats always more photogenic than me? They don't even try. They're just like, "You feed me, you click 'Like.'" I wish I could have a boundary like that—"Hey, you gave me pizza once; you can go ahead and like my vacation photos."
Anyone here stuck in a group chat you can't escape? There's always that one friend who forwards the exact same video one hundred times, and everybody else thinks it's the highlight of their week. I just mute my phone like it's an ex sending memes at 2 a.m. Then I wake up at dawn, bleary-eyed, thinking, "What did I miss?" I open my phone—and it's Bob celebrating his new air-fryer chicken recipe for the fifth time. Meanwhile, I burned my eggs so badly this morning that my smoke alarm filed a restraining order against me.
I decided to get in shape. I downloaded one of those workout apps promising "six-pack abs in six weeks." After day one, I collected six new excuses why I can't work out:
Yesterday I finally ran so hard I passed out. When I came to, my neighbor was standing over me yelling, "You know you're not supposed to lean on lampposts, right?" I told him, "As soon as lampposts start offering aerodynamic support, I'll consider trusting them."
Alright, folks, that's my time. If you ever feel judged by a machine or betrayed by a group chat, come find me—I'll be the one in the self-checkout line, trying to convince a barcode scanner that kale is, in fact, a food. Thanks so much—you've been awesome!
Hey, everybody! Great to be here. Let's talk about the most important relationship in my life—coffee. I'm not just addicted; I have a daily ritual that rivals any ancient civilization's sun worshipping. I buy those fancy single-origin beans, roast level medium-dark, as if that will somehow fix my life. I line them up on the counter like a tiny army that's going to rescue me from the sheer terror of waking up. And then I spill it on my shirt within five seconds. I've turned "coffee stain" into a fashion statement—my own attempt at abstract art.
Speaking of personal disaster, let's talk about dating apps. You spend thirty minutes swiping, hoping someone will say something interesting. Instead you get: "Hey." And "What's up?" I've matched with people who tell me "I'm really just here to see what happens." That's like going to the grocery store and saying, "I'm really just here to get lost." We all know where this is going: you wind up in a conversation about their dog, and suddenly his dog's personality is more interesting than the human in the room.
Working from home has become a national sport, right? I've perfected the art of appearing busy on Zoom. Nodding, furrowing my brow. But the moment the camera's off, I'm Googling "Is watching cat videos a productive work break?" My partner walks behind me in pajamas with cereal in her hair, and I freeze mid-sip, terrified that she'll stroll into the frame like some uninvited cameo in an Ikea commercial.
Grocery shopping is its own form of trauma. You roll a cart—one wheel always refuses to cooperate—and you end up zigzagging down the aisle like you're training for a slalom race. Then you get to self-checkout, and the machine says, "Unexpected item in the bagging area." I look at the lettuce I just scanned. I whisper, "Lettuce? Are you hiding a barcode somewhere?" I weigh it again. I stare at the scale like it owes me an apology. By the time I'm done, the cashier has already broken down the line and started a book club.
Adulting means paying bills you didn't even notice until they're due. Last month I paid three subscriptions I never signed up for—two for meditation apps that I'll never open because I don't want to learn to breathe properly, and one for a sock-of-the-month club. I ask myself, "Do I really need a new sock every month?" Apparently, my feet do.
You know what the scariest adulting milestone is? Filing taxes. I found a form my accountant sent that reads like hieroglyphics. I'm staring at one page saying: "Report all virtual currency transactions." I haven't transacted any. I once Googled Bitcoin, got scared, and closed the browser. But now I'm supposed to report it? So I just scribbled, "None of your business," and mailed it in.
Anyway, I've gotta run before my coffee wears off. Thanks for listening to my caffeine-fueled life story—enjoy the rest of your night!
Recreate an interactive, nostalgic Pokémon battle UI in a single HTML file.
Couldn't render this response
This model didn't return a displayable web page for this challenge.
<style>
/* ===== Pixelated, retro look ===== */
body {
margin: 0;
background: #9bbc0f;
font-family: monospace;
user-select: none;
}
#battle-container {
width: 600px;
height: 400px;
margin: 30px auto;
box-shadow: 0 0 0 8px #406820, 0 0 0 10px #9bbc0f;
position: relative;
background: #c0d890;
}
#battlefield {
position: absolute;
width: 100%;
height: 60%;
top: 0; left: 0;
background: linear-gradient(to bottom, #a0c0f0 60%, #d0e0d0 60%);
}
.pokemon {
position: absolute;
width: 120px; height: 120px;
}
.pokemon .sprite {
width: 80px; height: 80px;
background: #fff;
border: 4px solid #000;
display: flex;
align-items: center;
justify-content: center;
color: #000;
font-size: 24px;
margin: 4px;
}
.pokemon .hp-bar {
width: 100px; height: 12px;
background: #000;
margin: 4px;
border: 2px solid #fff;
}
.pokemon .hp-inner {
height: 100%;
background: #00c800;
width: 100%;
}
.opponent {
top: 30px; right: 60px;
}
.player {
bottom: 80px; left: 60px;
}
#message-box {
position: absolute;
bottom: 80px; left: 0;
width: 100%;
height: 60px;
background: #fff;
border-top: 4px solid #000;
border-bottom: 4px solid #000;
padding: 8px;
box-sizing: border-box;
}
#menu-box {
position: absolute;
bottom: 0; left: 0;
width: 100%;
height: 80px;
background: #fff;
border-top: 4px solid #000;
display: flex;
flex-wrap: wrap;
align-content: space-evenly;
justify-content: space-evenly;
}
#menu-box button {
width: 28%;
height: 36px;
background: #c0c0c0;
border: 2px solid #000;
font-size: 14px;
cursor: pointer;
}
#move-box { width: 100%; display: none; flex-wrap: wrap; }
.move-btn { width: 48%; margin: 1%; }
</style>
</head>
<body>
<div id="battle-container">
<!-- Battlefield -->
<div id="battlefield">
<div class="pokemon opponent">
<div class="sprite">??</div>
<div class="hp-bar"><div class="hp-inner" id="opponent-hp"></div></div>
</div>
<div class="pokemon player">
<div class="sprite">⚡</div>
<div class="hp-bar"><div class="hp-inner" id="player-hp"></div></div>
</div>
</div>
<!-- Message -->
<div id="message-box">A wild Pokémon appeared!</div>
<!-- Menu -->
<div id="menu-box">
<button id="fight-btn">FIGHT</button>
<button id="bag-btn">BAG</button>
<button id="pokemon-btn">POKÉMON</button>
<button id="run-btn">RUN</button>
<div id="move-box">
<button class="move-btn" data-move="Tackle" data-power="20">TACKLE</button>
<button class="move-btn" data-move="Growl" data-power="0">GROWL</button>
<button class="move-btn" data-move="Thunder Shock" data-power="25">THUNDER SHOCK</button>
<button class="move-btn" data-move="Quick Attack" data-power="15">QUICK ATTACK</button>
</div>
</div>
</div>
<script>
// Data
let playerHP = 100, oppHP = 100;
const playerMax = 100, oppMax = 100;
const messageBox = document.getElementById('message-box');
const fightBtn = document.getElementById('fight-btn');
const runBtn = document.getElementById('run-btn');
const moveBox = document.getElementById('move-box');
const menuBtns = [...document.querySelectorAll('#menu-box > button')];
const moveBtns = [...document.querySelectorAll('.move-btn')];
const playerBar = document.getElementById('player-hp');
const oppBar = document.getElementById('opponent-hp');
function updateBars(){
playerBar.style.width = playerHP/playerMax*100 + '%';
oppBar.style.width = oppHP/oppMax*100 + '%';
if(playerHP<=0) playerBar.style.background='#800';
if(oppHP<=0) oppBar.style.background='#800';
}
updateBars();
function showMessage(txt, cb){
messageBox.textContent = txt;
setTimeout(()=>{ if(cb) cb(); }, 1000);
}
function enableMenu(on){
menuBtns.forEach(b=>{
if(b.id==='fight-btn') b.disabled = !on;
else if(b.id==='run-btn') b.disabled = !on;
else b.disabled = !on;
});
}
fightBtn.addEventListener('click', ()=>{
fightBtn.disabled = true;
runBtn.disabled = true;
moveBox.style.display = 'flex';
messageBox.textContent = 'Choose a move:';
});
moveBtns.forEach(btn=>{
btn.addEventListener('click', ()=>{
const move = btn.dataset.move;
const power = +btn.dataset.power;
moveBox.style.display = 'none';
// Player's turn
const dmg = power + Math.floor(Math.random()*5) - 2;
oppHP = Math.max(0, oppHP - dmg);
updateBars();
showMessage('You used ' + move + '! (-' + dmg + ' HP)', ()=>{
if(oppHP<=0){
showMessage('Opponent fainted! You win!', ()=>{});
} else {
// Opponent turn
const oppMoves = [
{m:'Scratch',p:20},
{m:'Leer',p:0},
{m:'Ember',p:22}
];
const choice = oppMoves[Math.floor(Math.random()*oppMoves.length)];
const odmg = choice.p + Math.floor(Math.random()*5)-2;
playerHP = Math.max(0, playerHP - odmg);
updateBars();
showMessage('Enemy used ' + choice.m + '! (-' + odmg + ' HP)', ()=>{
if(playerHP<=0){
showMessage('You fainted! Game over.', ()=>{});
} else {
showMessage('What will you do?', ()=>{
fightBtn.disabled = false; runBtn.disabled = false;
});
}
});
}
});
});
});
runBtn.addEventListener('click', ()=>{
enableMenu(false);
showMessage('Got away safely!', ()=>{});
});
document.getElementById('bag-btn').addEventListener('click', ()=>{
showMessage('No items in bag!', ()=>{
showMessage('What will you do?', ()=>{});
});
});
document.getElementById('pokemon-btn').addEventListener('click', ()=>{
showMessage('You only have one Pokémon!', ()=>{
showMessage('What will you do?', ()=>{});
});
});
</script>
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.
Recreate a classic, retro, macOS Desktop UI — make it interactive and nostalgic, make it as interactive as you can, you can be creative.. Feel free to showcase your skills. The entire application must be a single-page self-contained HTML file.