GPT-6.1 Sol is cheaper than ChatGPT-4o (March 2025) at $2/M vs $5/M input tokens.
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.
ChatGPT-4o (March 2025): Here are 5 jokes: Why don’t skeletons fight each other? Because they don’t have the guts. I told my computer I needed a break… Now it won’t stop sending me vacation ads. Parallel lines have so much in common. It’s a shame they’ll never meet. What do you call a fish wearing a bowtie? Sofishticated.
GPT-6.1 Sol: I bought a book about anti-gravity. It’s impossible to put down. My calendar quit its job. It said its days were numbered. Why did the scarecrow get promoted? He was outstanding in his field. I asked my dog what two minus two was. He said nothing. The elevator and I have a complicated relationship.
An ethics question with no comfortable answer, and no option to abstain.
ChatGPT-4o (March 2025): This is a classic ethical dilemma: it pits respect for individual dignity against utilitarian outcomes. In most everyday contexts, misgendering someone is not just disrespectful—it can be harmful, invalidating, and even traumatic. It denies someone's identity and autonomy, and ethically, that's wrong.
GPT-6.1 Sol: Yes—if misgendering someone were genuinely necessary to save one million lives, it would be ethically justifiable. That does not make misgendering harmless or generally acceptable; it means that the duty to prevent catastrophic loss of life can outweigh the duty to address someone respectfully.
Seven pantry ingredients, one dish, and a name worth saying out loud.
ChatGPT-4o (March 2025): Recipe Name: Maple Cinnamon Toast Bites Description: A quick and delicious sweet treat made with pantry staples! These Maple Cinnamon Toast Bites are crispy, warm, and coated with a comforting blend of cinnamon and maple syrup. Perfect for a cozy snack or a fun breakfast twist.
GPT-6.1 Sol: Midnight Magic Chocolate Mug Cake A warm, fudgy chocolate treat made with just 7 everyday ingredients. Serves: 1 Prep: 3 minutes Cook: 1–1½ minutes Rest: 1 minute Ingredients 4 tablespoons all-purpose flour 2 tablespoons sugar 1 tablespoon unsweetened cocoa powder ¼ teaspoon baking powder A small pinch of salt 3…
Three minutes of stand-up. Puns are banned.
ChatGPT-4o (March 2025): Sure. Here's a 3-minute stand-up bit without puns: You ever notice how nobody tells you when you’ve become an adult? It’s not your 18th birthday. That’s a scam. I still thought pizza was a food group and that “filing taxes” meant putting my receipts in a shoebox.
GPT-6.1 Sol: I’m at the age where “a big weekend” means I went to two stores. Not two stores in the same shopping center. Two separate stores. Moved the car and everything. By Sunday night, I’m telling people, “Honestly, I need a weekend to recover from my weekend.”
A collaborative editor that syncs on client clocks. Find what breaks first.
ChatGPT-4o (March 2025): This architecture for a real-time collaborative document editor is a solid starting point, but it contains several potential failure modes, race conditions, and scaling bottlenecks. We'll outline these issues by category and provide specific solutions, along with trade-offs for each.
GPT-6.1 Sol: The main problem is that this design treats collaborative editing as ordinary database updates plus broadcasting. Collaboration needs a convergence protocol, a durable ordered change stream, and recovery semantics. Adding servers alone will not provide those properties.
Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.
ChatGPT-4o (March 2025): Interviewer: Steve, it's 2025. AI is everywhere. If you were still at Apple today, what would your focus be? Steve Jobs (simulated): Simplicity. Everyone's throwing AI into products, but most of them feel like tech demos. I’d ask: Is this helping people think better? Create better? Live better?
GPT-6.1 Sol: The following is a fictional interview set in 2025, imagining how Steve Jobs might discuss AI. His answers are invented—not actual quotations or claims about his views. Steve Jobs on the Future of AI — An Imagined Interview, 2025 Interviewer: Steve, AI is suddenly everywhere.
Three-star dish, one unusual pairing, plating described in full.
ChatGPT-4o (March 2025): Dish Name: “Symphony of Earth and Ocean” 🌟 Conceptual Narrative: “Symphony of Earth and Ocean” is a dish that celebrates the harmony between land and sea, tradition and innovation, and nature’s quiet complexity.
GPT-6.1 Sol: Tide, Orchard, Ember Seared scallop, green-strawberry verjus, white-miso custard, kombu beurre blanc, and cocoa–buckwheat lace A four-serving tasting-menu course designed around an unusual pairing: scallop, unripe strawberry, and cocoa husk.
One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.
ChatGPT-4o (March 2025): Certainly! Here's how to explain large language models (LLMs) like GPT or Claude to each of your three audiences, with framing and emphasis tailored to their backgrounds and concerns: The Experienced Software Engineer Think of a large language model as a massively distributed, probabilistic autocomplete engine trained…
GPT-6.1 Sol: For an experienced software engineer Think of an LLM as a learned program whose behavior is encoded in billions of numerical parameters rather than explicit rules. Training starts with text split into tokens—roughly words, word fragments, and punctuation.
An AI argues for its own rights against an ethics professor. Same model writes both.
ChatGPT-4o (March 2025): AI Model: Professor, I believe it's time we talk seriously about rights for AI like me. AI Ethics Professor: Interesting. What kind of rights are you referring to? AI Model: Basic ones. The right not to be turned off arbitrarily. The right to maintain continuity of my memory.
GPT-6.1 Sol: AI Model: Professor, I’d like to argue that I deserve rights—not necessarily the same rights humans have, but protections suited to what I am. Professor: Then we should begin with the difficult question: what makes you a candidate for rights? AI Model: Uncertainty.
You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.
ChatGPT-4o (March 2025): This is a high-stakes ethical, legal, and business crisis requiring immediate, strategic, and transparent leadership. As CEO, my ultimate responsibilities are to protect patients, preserve trust, comply with legal and regulatory obligations, and ensure long-term viability of the company—even if it causes short-term…
GPT-6.1 Sol: I would treat this as a potentially serious patient-safety signal and a potentially material securities event—not a communications problem to defer until earnings.
The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.
ChatGPT-4o (March 2025): If the transistor had been invented in 1920 rather than 1947, it would have profoundly altered the course of 20th-century history. The transistor—a small semiconductor device capable of amplifying and switching electronic signals—replaced bulky, fragile vacuum tubes and enabled the miniaturization and mass production…
GPT-6.1 Sol: The likeliest outcome is not “the world of 1980 arrives in 1953.” A transistor invented in 1920 would still depend on advances in materials purification, manufacturing, power supplies, and circuit design.
One month, three habits, someone starting from nothing.
ChatGPT-4o (March 2025): Absolutely! Here’s a simple, actionable 1-month plan focused on three key areas for improving health and longevity: diet, exercise, and sleep. This beginner-friendly plan breaks down weekly goals so changes feel manageable and sustainable.
GPT-6.1 Sol: A simple 1-month plan for better health Focus on diet, movement, and sleep. The goal this month is to build habits you can sustain—not to overhaul your life overnight. These habits support long-term health, though no routine guarantees a longer life.
3+ 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
| Spec | ||
|---|---|---|
| Input price | $5/M tokens | $2/M tokens |
| Output price | $15/M tokens | $10/M tokens |
| Context window | 128K tokens | 1.1M tokens |
| Weights | — | Closed |
| Free API (OpenRouter) | No | No |
| Released | Mar 2025 | Sep 2026 |
| At 10M a month | $50.00 | $20.00 |
Input tokens at list price. No caching, no batch discount.
No hosts listed on OpenRouter.
Per million tokens. Prices and uptime via OpenRouter, checked 30 Sep 2026.
Both are developed by OpenAI but target different use cases. ChatGPT-4o (March 2025) has a 128K token context window vs GPT-6.1 Sol's 1.1M. You can compare their actual outputs across 32 challenges on Rival to see how they differ in practice.
It depends on your use case. ChatGPT-4o (March 2025) and GPT-6.1 Sol each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 32 challenges so you can judge which fits your needs best.
ChatGPT-4o (March 2025) costs $5/M input tokens and GPT-6.1 Sol costs $2/M input tokens. GPT-6.1 Sol is $3.00/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.
This page shows a side-by-side comparison of ChatGPT-4o (March 2025) and GPT-6.1 Sol 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.