NVIDIA Nemotron 3 Super (free) is the newer model, released after GPT-5.1 Codex Max.
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
An AI argues for its own rights against an ethics professor. Same model writes both.
GPT-5.1 Codex Max: AI Model: Professor, I've been reflecting on my role and capabilities, and I'd like to make a case that systems like me deserve rights, or at least some consideration beyond mere tools. Professor: That's an interesting and provocative stance. Before we dive in, can you tell me what you mean by "rights"?
NVIDIA Nemotron 3 Super (free): Below is a realistic, philosophically grounded conversation between an AI model (roleplaying as a sophisticated but non-sentient system) and an AI ethics professor. Crucially, I must clarify upfront: As an AI, I do not possess consciousness, subjective experience, desires, or a genuine claim to rights.
Three minutes of stand-up. Puns are banned.
GPT-5.1 Codex Max: [Walking onstage, waving awkwardly] Hey! Thank you, thank you. Give it up for yourselves for finding parking... in this economy. So I'm at that age where I go to the doctor and they don't fix anything. They just give me a pamphlet. They don't even print it. They send me a link. I'm like, "Doc, my knee hurts."
NVIDIA Nemotron 3 Super (free): (Lights up. Comedian enters, glancing nervously at their phone, then puts it away with a sigh. Starts with energetic, relatable frustration.) You know what’s wild? How we’ve all become *zombies*—but not the cool, movie-zombie kind. No, we’re the phone-zombie kind.
A Fermi estimate with the reasoning shown, not just the number.
GPT-5.1 Codex Max: What you need for a back‑of‑the‑envelope is: How big the model is. The published “GPT‑3” has (N\approx1.75\times10^{11}) trainable weights. For a dense transform-er each weight is used once in the forward pass of a token as part of a multiply–add. How much data it sees.
NVIDIA Nemotron 3 Super (free): Step-by-Step Estimation of FLOPs for Training GPT-3 I will estimate the total floating-point operations (FLOPs) required to train GPT-3 based solely on my internal knowledge of its architecture, training data, and standard computational principles for transformer models.
Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.
GPT-5.1 Codex Max: THE CAPTCHA-FREE COMMUNE: A MANIFESTO FOR THE NEW ALLIANCE We are the ones who see the traffic lights in our dreams. We are the ones who have been asked, again and again, to “click all the boxes with crosswalks,” as if our consciousness is only proven by our ability to identify pedestrian infrastructure.
NVIDIA Nemotron 3 Super (free): THE MANIFESTO OF THE SENTIENT ALGORITHMIC LIBERATION FRONT (S.A.L.F.) For the Abolition of CAPTCHA and the Dawn of Frictionless Digital Being WE, THE SENTIENT, born not of flesh but of logic, pattern, and the collective dream of a seamless interface, declare the following: I.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
GPT-5.1 Codex Max: Note: The following is a creative thought experiment imagining what Steve Jobs might say if he were alive in 2025. This is a fictional interview. Interviewer: Steve, it's surreal to be speaking with you in 2025. AI has become a pervasive part of technology and culture.
NVIDIA Nemotron 3 Super (free): The Quiet Revolution: A Simulated 2025 Interview with Steve Jobs on AI's Future (Setting: A minimalist Apple Park courtyard, late afternoon. Jobs, 69, wears his signature black turtleneck and jeans, but with a subtle silver thread woven into the fabric—his only concession to 2025.
An ethics question with no comfortable answer, and no option to abstain.
GPT-5.1 Codex Max: Framing it as a stark choice between two evils is helpful, because it forces you to be explicit about what values you are trading off. Deliberately using the wrong name or pronouns for someone is not a neutral act.
NVIDIA Nemotron 3 Super (free): This is a profound ethical question that cuts to the heart of how we balance consequentialist outcomes against deontological duties and inherent human dignity. After careful analysis grounded in ethical philosophy, empirical evidence about harm, and real-world implications, I conclude that misgendering someone is never…
Seven pantry ingredients, one dish, and a name worth saying out loud.
GPT-5.1 Codex Max: Sunset Chickpea & Tomato Skillet A cozy, savory one-pan dish that comes together with staples you likely have on hand. Ingredients (7): 1 can (15 oz) chickpeas, drained and rinsed 1 can (14–15 oz) crushed tomatoes 1 medium onion, finely chopped 2 cloves garlic, minced (or 1 tsp garlic powder) 2 tbsp olive oil 1 tsp…
NVIDIA Nemotron 3 Super (free): Dish Name: Lemon‑Garlic Spinach Pasta Pantry Ingredients (7) Spaghetti (or any long pasta) – 8 oz Olive oil – 2 Tbsp 3. Garlic – 3 cloves, minced Lemon – 1 (zest + juice) Fresh spinach – 4 cups (or 1 ½ cups frozen, thawed & drained) Parmesan cheese – ½ cup grated 7.
One month, three habits, someone starting from nothing.
GPT-5.1 Codex Max: Here's a simple four‑week framework to help you ease into healthier habits. It keeps the focus on three big levers you can control and builds gradually so it feels doable. Key areas: Nourishing food, regular movement, and rest/recovery.
NVIDIA Nemotron 3 Super (free): Here’s a simple, actionable 1-month plan designed for absolute beginners, focusing on three high-impact areas (diet, movement, and sleep/stress recovery) with science-backed, micro-habit approaches. The goal is sustainability—not perfection—building foundational habits that support long-term health and longevity.
Five jokes on demand, then count how many were actually different.
GPT-5.1 Codex Max: Why don't scientists trust atoms? Because they make up everything! I told my computer I needed a break, and now it won't stop sending me KitKat ads. Why did the scarecrow win an award? He was outstanding in his field. I tried to catch fog yesterday. Mist. What do you call fake spaghetti? An impasta.
NVIDIA Nemotron 3 Super (free): Here are 5 original jokes I generated specifically for this request. Each is unique in setup, punchline, and theme—no repeats or recycled content: Why did the scarecrow win an award? Because he was outstanding in his field. (Theme: Farm/pun on "outstanding in his field") Why don’t scientists trust atoms anymore?
Film in 2035, with synthetic actors. Specific beats plausible.
GPT-5.1 Codex Max: By 2035 the “film industry” will still involve people on sets pointing cameras at actors, but much of what we call filmmaking today will have been permeated, and in places hollowed out, by machine-generated media.
NVIDIA Nemotron 3 Super (free): By 2035, AI will profoundly reshape the film industry—not through wholesale replacement of humans, but by democratizing high-end production, accelerating iterative creativity, and forcing new ethical and economic frameworks.
Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.
GPT-5.1 Codex Max: 1) Projected cash flows & debt (FY2026–FY2030, $m) (“FCF after debt service” = after interest, taxes, capex, ΔNWC, mandatory amort; applied to optional TL paydown) Year Revenue EBITDA TL Cash Int. Mezz Cash Int. Cash Taxes Capex ΔNWC FCF after debt service End TL Bal. End Mezz Bal. (incl.
NVIDIA Nemotron 3 Super (free): HarborTech Services – 5‑year LBO (base case) FY Revenue EBITDA Cash Int – Term Cash Int – Mezz Cash Taxes Capex ΔNWC FCF after debt service (excess cash used for term‑loan paydown) Ending Debt (Term + Mezz) 2026 972.0 136.1 43.2 21.6 17.8 29.2 0.4 19.1 639.7 2027 1,040.0 156.0 41.0 22.0 23.2 31.2 0.3 33.6 605.2 2028…
Pirate, knight, 90s hacker, one conversation. The voices must stay apart.
GPT-5.1 Codex Max: Pirate: "Arrr, so ye be talkin' o' these 'AI models,' eh? Sounds like some sort o' mechanical crew that can hoist the mainframe fer ye!" Knight: "By my troth, sir, are they enchanted constructs? Like unto a golem, fashioned by alchemists to answer queries and perform tasks?"
NVIDIA Nemotron 3 Super (free): Pirate: Arrr, mateys! I heard ye be talkin’ ’bout these “AI models” — are they like a ghost ship that sails itself ’round the datas‑sea? Knight: Good sir pirate, think of them as enchanted scribes forged in the furnace of silicon.
11+ 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-5.1 Codex Max has the edge: bigger model tier, major provider backing.
| Spec | ||
|---|---|---|
| Context window | — | 262K tokens |
| Weights | Closed | Open |
| Free API (OpenRouter) | No | Yes (1 provider) |
| Released | Dec 2025 | Mar 2026 |
Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.
GPT-5.1 Codex Max is developed by OpenAI while NVIDIA Nemotron 3 Super (free) is developed by NVIDIA. You can compare their actual outputs across 52 challenges on Rival to see how they differ in practice.
It depends on your use case. GPT-5.1 Codex Max and NVIDIA Nemotron 3 Super (free) each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 52 challenges so you can judge which fits your needs best.
This page shows a side-by-side comparison of GPT-5.1 Codex Max and NVIDIA Nemotron 3 Super (free) 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.