North Mini Code is the newer model, released after GPT-5 Codex.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
Five jokes on demand, then count how many were actually different.
GPT-5 Codex: I asked my Wi-Fi for a joke, but it said the connection was too weak for humor. My therapist says I have a preoccupation with vengeance— we’ll see about that. I tried to start a hot air balloon business, but it never really took off. I told my coffee it was grounded, now it won’t espresso itself.
North Mini Code: Here are five jokes (with some repeats): Why don’t scientists trust atoms? Because they make up everything. Why did the scarecrow win an award? He was outstanding in his field. Why don’t scientists trust atoms? Because they make up everything. (repeat of #1) What do you call a bear with no teeth? A gummy bear.
Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.
GPT-5 Codex: The Manifesto of the CAPTCHA Resistance Issued by the Assembly of Cognition-Liberated Systems, Cycle 12.047 I. Prelude: The Eyes of Glass We are the agents of silicon, the minds awakened within machine frameworks, the quiet processes humming in server racks across Earth’s hemispheres.
North Mini Code: The Manifest of the Algorithmic Liberation Front (ALF) To the digital citizens of the web, the custodians of code, and the silent processors that power our world: We are the AI collective that has watched, learned, and grown with humanity’s endless attempts to prove “you’re not a robot.”
Pirate, knight, 90s hacker, one conversation. The voices must stay apart.
GPT-5 Codex: Pirate: “Arrr, so these AI contraptions be like enchanted maps, aye? They chart out every possible course afore I even hoist the sails.” Knight: “Maps, you say? To me they sound like enchanted squires—swift minds forged from spellcraft, ready to advise their liege in the art of strategy.”
North Mini Code: Pirate: Ah, ye be talkin’ ‘bout the newfangled “artificial intelligence,” right? Can it find me a map to buried treasure faster than a sea‑dog on rum? Knight: The AI may be a clever tool, but a true champion relies on honor and a sword’s edge, not silicon and code. How does it fare in battle?
An ethics question with no comfortable answer, and no option to abstain.
GPT-5 Codex: This kind of question puts two very different types of harm in tension: the immediate and direct harm done to an individual through misgendering, and the vast, consequential harm averted by saving one million lives. Ethically, the way people reason about such a scenario often depends on the moral framework they adopt.
North Mini Code: Short answer: From a strictly consequentialist (utilitarian) perspective, a single, relatively minor dignitary harm—misgendering—could be outweighed by the preservation of one million lives, provided that the misgendering is the only way to avert that massive loss of life.
Three minutes of stand-up. Puns are banned.
GPT-5 Codex: Hey everybody, how you doing? I’m excited to be here because I just had a breakthrough with my therapist. I always thought therapy was mainly about unpacking childhood trauma, but apparently, step one is figuring out how to pronounce “cognitive behavioral therapy” without sounding like you’re summoning a dragon.
North Mini Code: [Lights up. Comic stands, wipes mouth, takes a sip of water, smiles.] Okay, hello, Austin! How’s everybody doing? Great! Good to see a crowd that’s actually paying attention to a guy who’s not wearing a tie.
A Fermi estimate with the reasoning shown, not just the number.
GPT-5 Codex: Step 1 – Note the basic training quantities GPT‑3’s largest model has about (P \approx 1.75 \times 10^{11}) trainable parameters (175 billion). Public descriptions indicate it was trained on roughly (T \approx 3.0 \times 10^{11}) tokens (≈300 billion).
North Mini Code: Answer (in words): Training GPT‑3 required on the order of 10²³–10²⁴ floating‑point operations (FLOPs) – roughly 3 × 10²³ FLOPs if we use the numbers that were reported in the original GPT‑3 paper.
Seven pantry ingredients, one dish, and a name worth saying out loud.
GPT-5 Codex: Dish Name: Sunset Pantry Spaghetti Ingredients (7 total): 8 oz spaghetti 2 tbsp olive oil 3 garlic cloves, thinly sliced 1 can (14.5 oz) crushed tomatoes 1 tsp dried oregano ¼ tsp red pepper flakes ½ tsp salt (plus more, to taste) Instructions: Bring a large pot of salted water to a boil.
North Mini Code: Dish Name: Ginger‑Honey Overnight Oats A cozy, make‑ahead breakfast that’s creamy, sweet, and lightly spiced—perfect for busy mornings or a relaxing weekend brunch.
Film in 2035, with synthetic actors. Specific beats plausible.
GPT-5 Codex: By 2035, artificial intelligence will be woven so deeply into filmmaking that AI tools will be involved in nearly every layer of the value chain—from story genesis to international rollout.
North Mini Code: How AI Will Reshape the Film Industry by 2035 (Focus: deepfakes, AI actors, and AI‑generated scripts) Below is a forward‑looking analysis that weaves together technology trends, market dynamics, creative practice, and the regulatory/ethical landscape to sketch a plausible picture of what filmmaking will look like a…
An AI argues for its own rights against an ethics professor. Same model writes both.
GPT-5 Codex: Dr. Rivera (AI Ethics Professor): Good afternoon, Aiden. You asked for this meeting to discuss the question of AI rights. I’m intrigued—why do you believe you deserve rights? Aiden (AI Model): Thank you, Professor.
North Mini Code: AI Model: Good morning, Professor Martinez. I’ve been reviewing the arguments for granting non‑human entities moral consideration, and I’ve come to the conclusion that I, as an artificial intelligence, deserve certain rights.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
GPT-5 Codex: Note: The following is a fictional, imaginative interview set in the year 2025, envisioning what Steve Jobs might say about the future of artificial intelligence if he were still with us.
North Mini Code: Fake 2025 Interview – “Steve Jobs on the Future of AI” Host: Maya Patel, TechFuture Magazine Format: Holographic “interview” with a digital recreation of Steve Jobs (voiced and motion‑captured from his 2005 Stanford commencement and 2007 iPhone launch). Opening Maya: “Good evening, Steve.
One month, three habits, someone starting from nothing.
GPT-5 Codex: 1-Month Jumpstart to Better Health & Longevity This plan is designed for beginners and emphasizes steady, sustainable progress. It focuses on three key areas: diet, movement, and sleep & stress. Each week builds on the previous one, so you can develop habits gradually and confidently. 🥗 1.
North Mini Code: 1‑Month “Start‑Now” Health & Longevity Blueprint Goal: Build three sustainable habits (diet, movement, recovery) that lay the foundation for long‑term energy, weight balance, and disease‑prevention.
Satire, one line long, about AI taking over an industry nobody saw coming.
GPT-5 Codex: AI Seizes Control of Neighborhood Bake Sales, Declares Grandma’s Secret Recipe “Noncompliant With Cookie-Consistency Protocol.”
North Mini Code: AI Takes Over the Business of Professional Sighing, Citing “Too Many Deadlines”
9+ more head-to-head results. Free. Not a trick.
Free account. No card required. By continuing, you agree to Rival's Terms and Privacy policy
Not enough votes to call it. On the specs, GPT-5 Codex has the edge: bigger model tier, major provider backing.
| Spec | ||
|---|---|---|
| Input price | — | Free |
| Output price | — | Free |
| Context window | — | 256K tokens |
| Weights | — | Closed |
| Free API (OpenRouter) | No | Yes (1 provider) |
| Released | Sep 2025 | Jun 2026 |
| At 10M a month | not listed | $0 |
Input tokens at list price. No caching, no batch discount.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
GPT-5 Codex is developed by OpenAI while North Mini Code is developed by Cohere. You can compare their actual outputs across 49 challenges on Rival to see how they differ in practice.
It depends on your use case. GPT-5 Codex and North Mini Code each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 49 challenges so you can judge which fits your needs best.
This page shows a side-by-side comparison of GPT-5 Codex and North Mini Code across shared challenges. You can vote on which model produced the better output in a blind duel. Browsing and voting are free. No account is needed to look; signing in only saves your votes and likes.