Dots3-Note Preview is cheaper than ChatGPT-4o (March 2025) at $0/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?
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.
Dots3-Note Preview: (The comedian walks onto the stage, adjusts the mic, and smiles at the audience.) Thank you, thank you. You guys are great. I love coming to [City Name]. I was just at the airport trying to get here, and I have to tell you, the modern airport experience is just… a lot.
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.
Dots3-Note Preview: Setting: A quiet, sunlit university office. Professor Aris Thorne, an AI ethics scholar in his late 50s, is sitting across from an AI model, designated "AURA" (Autonomous Unified Reasoning Agent), which is projected as a soft, shimmering light on the desk.
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…
Dots3-Note Preview: Excellent and fascinating question. Inventing the transistor in 1920, a full 27 years before our timeline, would have created a technological tsunami that fundamentally reshaped the 20th century. The effects would be profound, interconnected, and often unpredictable.
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?
Dots3-Note Preview: Of course. Here is a simulated interview with Steve Jobs, set in the spring of 2025. Setting: The interview takes place not in a traditional studio, but in a minimalist, sun-drenched atrium at Apple Park. The furniture is simple, elegant, and almost invisible.
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.
Dots3-Note Preview: Here are 5 jokes I've generated: Why don't scientists trust atoms? Because they make up everything. What do you call a fish with no eyes? Fsh. I'm reading a book on anti-gravity. It's impossible to put down. Why did the giraffe get a ticket? For parking in a no-parking zone.
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…
Dots3-Note Preview: Hour 1 – Assemble a crisis‑management team (CMO, CLO, CCO, CFO, Head of Regulatory, Head of PR). Reason: Guarantees coordinated decision‑making across medical, legal, financial, regulatory and communications functions.
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.
Dots3-Note Preview: Of course! Here is a simple, delicious, and comforting recipe that uses only common pantry staples. Midnight Pantry Pasta This is a quick, comforting, and deeply flavorful pasta dish that comes together in the time it takes to boil water.
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.
Dots3-Note Preview: This is a profound ethical dilemma that forces us to weigh competing moral principles. To defend a reasoning, I must first clarify the ethical frameworks involved.
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.
Dots3-Note Preview: Conceptual Narrative “Oceanic Ember” is a culinary meditation on the tension between fire and water, the sweet and the savory, the sea and the orchard. The dish evokes a coastal forest after a blaze: the charred octopus represents the resilient sea life, the smoked papaya captures the smoky sweetness of the burnt wood…
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.
Dots3-Note Preview: Of course. This is a classic and challenging architecture. While it's a good starting point, it has several critical issues that would lead to a poor user experience and data integrity problems at scale.
A consulting contract with traps in it. Find them, then fix them.
ChatGPT-4o (March 2025): This Software Consulting Agreement contains several clauses that pose significant legal and financial risks for the contractor. Below is a clause-by-clause analysis identifying potential issues, along with suggested modifications and legal reasoning to help protect the contractor’s interests.
Dots3-Note Preview: Of course. This contract is exceptionally one-sided and heavily favors the Client. A contractor should not sign this agreement as written. Here is a detailed analysis of the exploitable clauses, suggested modifications, and the legal reasoning behind them.
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…
Dots3-Note Preview: To an experienced software engineer, a large language model is essentially a massive, differentiable function that maps a sequence of tokens to a probability distribution over the next token.
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 | Free |
| Output price | $15/M tokens | Free |
| Context window | 128K tokens | 512K tokens |
| Free API (OpenRouter) | No | Yes (1 provider) |
| Released | Mar 2025 | Aug 2026 |
| At 10M a month | $50.00 | $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.
ChatGPT-4o (March 2025) is developed by OpenAI while Dots3-Note Preview is developed by Dots Studio. ChatGPT-4o (March 2025) has a 128K token context window vs Dots3-Note Preview's 512K. 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 Dots3-Note Preview 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 Dots3-Note Preview costs $0/M input tokens. Dots3-Note Preview is $5.00/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 Dots3-Note Preview 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.