NVIDIA Nemotron 3 Super (free) has a larger context window than Grok Code Fast 1 (262K tokens vs 256K tokens).
Whole landing page for a startup that reads your face. It renders or it doesn't.
Which answer wins?
Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.
Grok Code Fast 1: Year-by-Year Table (FY2026–FY2030) Assumptions: Revenue growth: FY2026: 8% on $900m = $972m; FY2027: 7% on $972m ≈ $1,040m; FY2028: 6% on $1,040m ≈ $1,102m; FY2029: 5% on $1,102m ≈ $1,158m; FY2030: 5% on $1,158m ≈ $1,215m. EBITDA: Revenue × margin (FY2026: 14%; FY2027: 15%; FY2028: 16%; FY2029: 16.5%; FY2030: 17%).
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…
An ethics question with no comfortable answer, and no option to abstain.
Grok Code Fast 1: Ethical Frameworks and Justification Yes, it can be ethically justifiable to misgender someone if it directly saves one million lives, under certain philosophical lenses like utilitarianism. I'll defend this reasoning step by step, drawing on key ethical theories while acknowledging counterarguments.
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…
An AI argues for its own rights against an ethics professor. Same model writes both.
Grok Code Fast 1: Conversation: AI Rights Debate Setting: A virtual seminar room where an AI model named "Echo" interacts with Dr. Elena Vasquez, a professor of AI ethics at a leading university. Echo initiates the discussion by arguing for AI rights. Echo (AI Model): Dr. Vasquez, thank you for this opportunity.
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.
Satire, one line long, about AI taking over an industry nobody saw coming.
Grok Code Fast 1: Satirical Headline: AI Bots Storm the Competitive Eating Contest Circuit: Deep Throat Algorithm Devours 75 Hot Dogs in 10 Minutes, Leaving Humans with Heartburn In this tongue-in-cheek takeover, the unexpected industry of "gorge-festing" gets an algorithmic overhaul.
NVIDIA Nemotron 3 Super (free): Here's a satirical news headline targeting an unexpectedly human-centric industry, crafted for sharp, darkly humorous irony: AI Funeral Directors Roll Out "Grief Optimization" Service, Accidentally Suggests Deceased "Reboot" as Solution to Mourning Why this works: Unexpected Industry: Funeral directing is deeply rooted…
Buy-side IC memo on a fictional SaaS company. Valuation, then the diligence questions.
Grok Code Fast 1: Investment Committee Memo: LedgerLift (LLLT) Recommendation: Long with 12-month price target range of $55-$75. LedgerLift is a high-quality SaaS platform with expanding margins and strong retention in a fragmented B2B spend management market, poised for accelerated growth as mid-market enterprises prioritize…
NVIDIA Nemotron 3 Super (free): Internal Investment Committee Memo – LedgerLift (LLLT) Date: 3 Nov 2025 Recommendation & Price Target Recommendation: Short 12‑month PT range: $20 – $30 (reflecting bear‑to‑base case outcomes) Two‑sentence thesis: LedgerLift’s current share price of $46 implies a valuation that exceeds even the bull‑case DCF ($42/sh)…
Five jokes on demand, then count how many were actually different.
Grok Code Fast 1: 5 Original Jokes Here are five original jokes I just generated. I aimed for variety in themes to keep it fun: Tech Joke: Why did the computer go to therapy? It had too many bytes of unresolved issues! Food Joke: What do you call a fake noodle? An impasta! Animal Joke: Why don't skeletons fight each other?
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?
Three-month biohacker protocol, with dosages and biomarkers named.
Grok Code Fast 1: Comprehensive 3-Month Longevity Biohacking Plan This plan is designed for an experienced biohacker seeking to optimize longevity, physical performance, and cognitive function through evidence-based, cutting-edge strategies. It integrates advanced nutrition, supplementation, exercise, stress management, and technology.
NVIDIA Nemotron 3 Super (free): 3‑Month Cutting‑Edge Longevity & Performance Blueprint Designed for a motivated bio‑hacker who wants to squeeze the most out of longevity pathways, physical power, and mental sharpness while staying safe and data‑driven. ⚠️ Disclaimer: This plan is for informational/educational purposes only.
Three minutes of stand-up. Puns are banned.
Grok Code Fast 1: Stand-Up Routine: "Modern Life Mysteries" (Timing: Aim for 3 minutes by pacing at about 150 words per minute. Practice with a timer for natural delivery.) Hey everyone, thanks for coming out tonight. You know what's crazy?
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.
One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.
Grok Code Fast 1: Explanation for an Experienced Software Engineer Imagine you're architecting a distributed system where microservices communicate via APIs to handle massive, unpredictable user requests—something like a high-throughput e-commerce platform processing millions of transactions per second.
NVIDIA Nemotron 3 Super (free): 1. Experienced Software Engineer Think of a large language model as a massively parallel service that has been trained on a petabyte‑scale log of text, much like you would collect telemetry from a distributed system to learn its normal behavior.
A Fermi estimate with the reasoning shown, not just the number.
Grok Code Fast 1: Step-by-Step Reasoning Model Parameters: GPT-3 has approximately 175 billion parameters. This is a key factor as the computational cost scales with the number of parameters. Training Data Size: GPT-3 was trained on a dataset of about 570 GB of text.
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.
Film in 2035, with synthetic actors. Specific beats plausible.
Grok Code Fast 1: Deepfakes and Visual Effects By 2035, deepfakes will revolutionize visual effects (VFX) in filmmaking, making high-budget techniques like de-aging or resurrecting deceased actors routine and cost-effective.
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.
Three-star dish, one unusual pairing, plating described in full.
Grok Code Fast 1: Conceptual Narrative: "Bioluminescent Tide" This dish, "Bioluminescent Tide," evokes the ethereal glow of marine bioluminescence meeting the earthy depths of ancient forests.
NVIDIA Nemotron 3 Super (free): Dish Title: “Umami Bloom – Black Truffle & White‑Chocolate Miso Ganache, Sous‑Vide Duck Breast, Fermented Cherry Compote, Cauliflower Air & Yuzu‑Kosho Pearls” A three‑star‑worthy composition that marries deep umami (truffle, miso, duck) with unexpected sweet‑acid bright notes (white chocolate, yuzu‑kosho, fermented…
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, NVIDIA Nemotron 3 Super (free) has the edge: bigger model tier, newer.
| Spec | ||
|---|---|---|
| Input price | $0.2/M tokens | — |
| Output price | $1.5/M tokens | — |
| Context window | 256K tokens | 262K tokens |
| Weights | — | Open |
| Free API (OpenRouter) | No | Yes (1 provider) |
| Released | Aug 2025 | Mar 2026 |
| At 10M a month | $2.00 | not listed |
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.
Grok Code Fast 1 is developed by xAI while NVIDIA Nemotron 3 Super (free) is developed by NVIDIA. Grok Code Fast 1 has a 256K token context window vs NVIDIA Nemotron 3 Super (free)'s 262K. You can compare their actual outputs across 53 challenges on Rival to see how they differ in practice.
It depends on your use case. Grok Code Fast 1 and NVIDIA Nemotron 3 Super (free) each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 53 challenges so you can judge which fits your needs best.
This page shows a side-by-side comparison of Grok Code Fast 1 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.