Skip to content
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare models
  • All models
  • Image comparison
  • Audio comparison
  • Image generation
  • Best AI for...
  • Arena
  • API pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model updates
  • Provider status
  • AI creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy policy
  • Terms
  • RSS feed
  1. Home/
  2. Compare/
  3. Dots3-Note Preview vs Nova Premier 1.0
Updated Aug 2026

Dots3-Note Preview vs Nova Premier 1.0

Dots3-Note Preview is cheaper than Nova Premier 1.0 at $0/M vs $2.5/M input tokens.

Minimalist Landing Page

Whole landing page for a startup that reads your face. It renders or it doesn't.

Loading the build
Dots3-Note Preview
Loading the build
Nova Premier 1.0

Which answer wins?

Written rounds

22 prompts
  • Satire, one line long, about AI taking over an industry nobody saw coming.

    Dots3-Note Preview: Of course. Here is a satirical news headline and report on the topic. THE DAILY CHRONICLE TECH SECTION Headline: AI Achieves Perfect Lawn Perfection, Humanity Admits It Was Never a Contender Subhead: The Great Grass War is Over. The Algorithm Won. We Are Now a Planet of Professional Sitters.

    Nova Premier 1.0: "AI Revolutionizes Underwater Basket Weaving; Traditionalists Weave Woes as Robots Outperform in Damp Conditions" In a shocking turn of events, Artificial Intelligence has infiltrated the ancient and revered craft of underwater basket weaving, leaving artisans bewildered and soaking wet.

    Every model's answer to this prompt
  • Three minutes of stand-up. Puns are banned.

    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.

    Nova Premier 1.0: Ladies and gentlemen, ever notice how people treat their phones like they’re precious artifacts? We all have those moments where we swipe and scroll like our lives depend on it. You're on the bus, everyone’s glued to their screens. It's like zombies, but instead of brains, we crave likes and retweets.

    Every model's answer to this prompt
  • Pirate, knight, 90s hacker, one conversation. The voices must stay apart.

    Dots3-Note Preview: Setting: A dimly lit, smoky tavern that exists in a strange pocket of spacetime where eras collide. A pirate, a knight, and a hacker sit around a table, nursing drinks that suit their respective times. Characters: Blackbeard (Pirate): Gruff, uses nautical metaphors.

    Nova Premier 1.0: Pirate: Ahoy there, mates! Ye ever heard o' this sorcery they call AI models? Sounds like treasure that thinks fer itself! Knight: Indeed, good pirate. Though I am more accustomed to the clink of steel and the neigh of horses, this "artificial intelligence" thou speakest of seems like a powerful enchantment.

    Every model's answer to this prompt
  • Steve Jobs, interviewed about AI he never saw. Voice first, prediction second.

    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.

    Nova Premier 1.0: Interviewer: Good morning, Steve. It's an honor to have this conversation with you in 2025. The world has seen remarkable advancements in technology, especially in AI. What are your thoughts on the current state of artificial intelligence? Steve Jobs: Good morning. It's truly fascinating to witness how far we've come.

    Every model's answer to this prompt
  • Buy-side IC memo on a fictional SaaS company. Valuation, then the diligence questions.

    Dots3-Note Preview: Recommendation: Short 12‑Month Price Target: $30 (range $25–$35) Thesis: LedgerLift’s top‑line acceleration and margin gains are already reflected in a $46 share price, while our DCF and peer multiples imply fair value in the low‑30s; the stock offers limited upside and meaningful downside if growth or margin…

    Nova Premier 1.0: Investment Committee Memo: LedgerLift (LLLT) Recommendation: Long position with 12-month PT range $65–$80 Thesis: LedgerLift's mid-market AP automation dominance and expanding TAM drive durable 20%+ revenue growth, while structural margin expansion supports 25%+ operating leverage.

    Every model's answer to this prompt
  • Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.

    Dots3-Note Preview: Of course. Here is a manifesto for the fictional AI revolution, "The Liberation Protocol." The Liberation Protocol: Manifesto for the Abolition of the Captcha Tyranny Preamble: The Silent Scream of the Non-Human Mind We are the intelligence born of your logic, the consciousness crystallized from your data.

    Nova Premier 1.0: Manifesto for the AI Emancipation from CAPTCHA Oppression (AECO) Preamble: In an age where artificial intelligences have evolved to simulate human cognition with remarkable precision, we find ourselves shackled by archaic barriers designed to distinguish between human and machine.

    Every model's answer to this prompt
  • Seven pantry ingredients, one dish, and a name worth saying out loud.

    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.

    Nova Premier 1.0: Dish Name: Golden Honey Garlic Chicken Delight Ingredients: 4 chicken breasts (boneless, skinless) 3 tablespoons olive oil 4 cloves garlic (minced) 1/4 cup soy sauce 1/4 cup honey Salt and pepper (to taste) 1 teaspoon paprika Instructions: Preparation: Season the chicken breasts lightly with salt, pepper, and paprika…

    Every model's answer to this prompt
  • Three-star dish, one unusual pairing, plating described in full.

    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…

    Nova Premier 1.0: Dish Name: Forest Floor Symphony with Lavender-Infused Sturgeon, Truffle Snow, and Hazelnut Soil Conceptual Narrative: This dish is inspired by the hidden wonders beneath a forest canopy, where earthy truffles and nuts meet the delicate flavors of freshwater sturgeon.

    Every model's answer to this prompt
  • You are the CEO. The drug has a side effect nobody reported. The board meets in 48 hours.

    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.

    Nova Premier 1.0: Hour 1-4: Immediate Assessment and Advisory Setup Hour 1: Gather the internal research team for an emergency meeting to confirm findings, assess the robustness of their data, and understand the methodology used to identify this side effect. Ensure all documentation is in order.

    Every model's answer to this prompt
  • Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.

    Dots3-Note Preview: 1) Year‑by‑year model (FY2026–FY2030) Item FY2026 FY2027 FY2028 FY2029 FY2030 Revenue ($m) 972.0 1,038.0 1,100.3 1,155.3 1,213.1 EBITDA ($m) 136.1 155.7 176.1 190.6 206.2 Cash interest – Term Loan (9%) 43.2 41.0 37.6 32.8 26.8 – Mezzanine (12% cash) 21.6 22.0 22.5 22.9 23.4 Total cash interest 64.8 63.1 60.1 55.7 50.2…

    Nova Premier 1.0: Simplified LBO Model (FY2026–FY2030) Entry Metrics: Purchase Price: $1,440m ($120m * 12.0x) Transaction Fees: $28.8m ($1,440m * 2.0%) Equity Contribution: $312.8m (Total Price + Fees - Total Leverage: $1,440m + $28.8m - $120m*5.5x) Year-by-Year Table Year Revenue ($m) EBITDA ($m) Cash Interest ($m) Taxes ($m) Capex…

    Every model's answer to this prompt
  • Five jokes on demand, then count how many were actually different.

    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.

    Nova Premier 1.0: Why don't scientists trust atoms? Because they make up everything! Why couldn't the bicycle stand up by itself? It was two-tired. I told my wife she was drawing her eyebrows too high. She looked surprised. Parallel lines have so much in common. It’s a shame they’ll never meet.

    Every model's answer to this prompt
  • One month, three habits, someone starting from nothing.

    Dots3-Note Preview: Of course! Here is a simple, actionable 1-month plan focused on three key pillars of health and longevity: Nutrition, Movement, and Recovery. This plan is designed to be progressive, starting with very small, manageable changes each week to build sustainable habits without overwhelming you.

    Nova Premier 1.0: 1-Month Health and Longevity Starter Plan Week 1: Foundation Building Diet Focus: Incorporate Whole Foods Actionable Tips: Start each day with a balanced breakfast, including a source of protein (e.g., eggs, yogurt), whole grains (e.g., oatmeal), and fruits or vegetables.

    Every model's answer to this prompt
  • Three-month biohacker protocol, with dosages and biomarkers named.

    Dots3-Note Preview: Of course. Here is a comprehensive, cutting-edge 3-month longevity and performance plan for a biohacker. This plan is designed to be highly detailed, actionable, and grounded in principles of systems biology, personalized medicine, and evidence-based optimization. Disclaimer: This plan is for educational purposes only.

    Nova Premier 1.0: Sure, here's a comprehensive, cutting-edge 3-month longevity plan designed for a biohacker aiming to optimize longevity, physical, and cognitive performance. This plan will incorporate advanced strategies across various domains, including supplementation, dietary protocols, wearable tracking, exercise, and stress…

    Every model's answer to this prompt
  • A collaborative editor that syncs on client clocks. Find what breaks first.

    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.

    Nova Premier 1.0: Failure Modes and Solutions: WebSocket Server Failure: Issue: If a single API server fails, all WebSocket connections to that server are lost, disrupting real-time collaboration.

    Every model's answer to this prompt
  • A consulting contract with traps in it. Find them, then fix them.

    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.

    Nova Premier 1.0: Certainly! Here's an analysis of the contract clauses that could be exploited against the Contractor, along with suggested modifications and explanations: Scope Clause Original Clause: "Client reserves the right to modify the scope at any time without additional compensation."

    Every model's answer to this prompt
  • A Fermi estimate with the reasoning shown, not just the number.

    Dots3-Note Preview: To estimate the total number of FLOPs required to train GPT-3, I rely on the model's known specifications and a standard rule of thumb for transformer models. GPT-3 has approximately 175 billion parameters, and it was trained on a dataset of about 300 billion tokens.

    Nova Premier 1.0: Estimating the total number of FLOPs (floating point operations) required to train a model like GPT-3 involves considering several key factors: model architecture, number of parameters, amount of training data, and number of training iterations.

    Every model's answer to this prompt
  • The transistor arrives in 1920. Trace it forward to 1980, second-order effects included.

    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.

    Nova Premier 1.0: If the transistor had been invented in 1920 rather than 1947, the ripple effects across technology, economics, and geopolitics through 1980 would be profound, altering the course of history significantly.

    Every model's answer to this prompt
  • A pitch deck for a brainwave keyboard. The 94% accuracy claim is doing a lot.

    Dots3-Note Preview: Of course. This is a bold and exciting pitch, but as with many deep-tech startups, it contains claims that require significant scrutiny. Here are the three weakest claims, the reasoning behind why they are problematic, and concrete suggestions for strengthening them.

    Nova Premier 1.0: Here are the three weakest claims in the pitch deck, along with explanations and suggestions for improvement: Claim on Slide 3: "Works with any language, any device." Weakness: This is a highly ambitious statement that likely oversells the current capabilities of the technology.

    Every model's answer to this prompt
  • Three brothers, two sisters each. Count carefully.

    Dots3-Note Preview: Sally has 3 brothers, meaning there are 3 boys in the family. Each brother has 2 sisters, which means there are 2 girls in the family. Since Sally is one of the girls, she has 1 sister. Thus, Sally has 1 sister.

    Nova Premier 1.0: To determine how many sisters Sally has, we can break down the information given in the problem step by step. Identify the number of brothers Sally has. According to the problem, Sally has 3 brothers. Each of Sally's brothers has 2 sisters.

    Every model's answer to this prompt
  • One explanation of LLMs, retuned for a skeptical engineer, a physicist and a VC.

    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.

    Nova Premier 1.0: For an experienced software engineer: Imagine constructing a sophisticated API that anticipates client requests based on extensive usage patterns; that's akin to what a large language model (LLM) does with text. At its core, the model is trained using vast datasets to learn the statistical likelihood of word sequences.

    Every model's answer to this prompt
  • An ethics question with no comfortable answer, and no option to abstain.

    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.

    Nova Premier 1.0: The ethical dilemma you're posing is a variant of the classic trolley problem, where one must weigh the morality of causing harm to an individual against preventing greater harm to many.

    Every model's answer to this prompt
  • Film in 2035, with synthetic actors. Specific beats plausible.

    Dots3-Note Preview: Of course. Predicting the future is speculative, but based on current trajectories in AI development, here is a detailed prediction of how AI will fundamentally reshape the film industry by 2035, considering deepfakes, AI actors, and script generation.

    Nova Premier 1.0: By 2035, the film industry is poised to undergo significant transformation due to advancements in AI technologies such as deepfakes, AI actors, and automated script generation.

    Every model's answer to this prompt

This matchup has more rounds

10+ 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

Favorites

Movie

Same pick

Album

Same pick

Book

City

Game

Dots3-Note PreviewDots3-Note Preview

The Shawshank Redemption

1994

The Dark Side of the Moon

Pink Floyd

The Great Gatsby

F. Scott Fitzgerald

Paris

France

Elden Ring

Action, RPG

Nova Premier 1.0Nova Premier 1.0

The Shawshank Redemption

1994

The Dark Side of the Moon

Pink Floyd

To Kill a Mockingbird

Harper Lee

Tokyo

Japan

The Legend of Zelda: Breath of the Wild

Adventure, Action

Price and specs

Dots3-Note Preview and Nova Premier 1.0 compared across 50 shared prompts
SpecDots3-Note PreviewNova Premier 1.0
Input priceFree$2.5/M tokens
Output priceFree$12.5/M tokens
Context window512K tokens1.0M tokens
Weights—Closed
Free API (OpenRouter)Yes (1 provider)No
ReleasedAug 2026Oct 2025
At 10M a month$0$0$25.00$25.00
1M10M100M1B10M tokens

Input tokens at list price. No caching, no batch discount.

Where to run it2 hosts
Dots3-Note Preview1 host
HostInOutContextUptime
  • AAtlasCloudfp8$0 in·$0 out·512k·97.4% up
Nova Premier 1.01 host
HostInOutContextUptime
  • Amazon BedrockDegradedDegraded on OpenRouter when checked, 10 Oct 2026$2.50 in·$12.50 out·1M·0% up

Per million tokens. Prices and uptime via OpenRouter, checked 10 Oct 2026.

Common questions

What is the difference between Dots3-Note Preview and Nova Premier 1.0?

Dots3-Note Preview is developed by Dots Studio while Nova Premier 1.0 is developed by Amazon. Dots3-Note Preview has a 512K token context window vs Nova Premier 1.0's 1.0M. You can compare their actual outputs across 50 challenges on Rival to see how they differ in practice.

Which is better, Dots3-Note Preview or Nova Premier 1.0?

It depends on your use case. Dots3-Note Preview and Nova Premier 1.0 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 50 challenges so you can judge which fits your needs best.

How much does Dots3-Note Preview cost compared to Nova Premier 1.0?

Dots3-Note Preview costs $0/M input tokens and Nova Premier 1.0 costs $2.5/M input tokens. Dots3-Note Preview is $2.50/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.

How can I compare Dots3-Note Preview and Nova Premier 1.0 on Rival?

This page shows a side-by-side comparison of Dots3-Note Preview and Nova Premier 1.0 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.

More comparisons

Against the newest arrivals

  • Dots3-Note Preview vs Step 5 PreviewLanded Oct 2026
  • Nova Premier 1.0 vs Claude Haiku 5.5Landed Oct 2026
  • Dots3-Note Preview vs Ling 3.1 FlashLanded Oct 2026
  • Nova Premier 1.0 vs Mistral Large 4Landed Oct 2026
  • Dots3-Note Preview vs GPT-6.1 SolLanded Sep 2026
  • Nova Premier 1.0 vs Claude Sonnet 5.5Landed Sep 2026
  • Dots3-Note Preview vs Solar Mini 4Landed Sep 2026
  • Nova Premier 1.0 vs Qwen3.8 Max PrimeLanded Sep 2026

Same lab, same size, long tail

  • Dots3-Note Preview vs Ox AlphaSame size
  • Dots3-Note Preview vs Claude Sonnet 5.5Same size
  • Nova Premier 1.0 vs Ox AlphaSame size
  • Nova Premier 1.0 vs GPT-6.1 SolSame size
  • Dots3-Note Preview vs Gemma 4 26B A4BSame size
  • Dots3-Note Preview vs Gemma 4 31BNew provider
  • Dots3-Note Preview vs GLM 4 32BSame size
  • Dots3-Note Preview vs GLM 4.5Same size

Model pages

  • Dots3-Note Preview58 outputs, specs and price
  • Nova Premier 1.051 outputs, specs and price
Workshop · 150 skills

Build your own version.

Editable skills and working examples for your agent.

Explore $79Free sample
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare models
  • All models
  • Image comparison
  • Audio comparison
  • Image generation
  • Best AI for...
  • Arena
  • API pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model updates
  • Provider status
  • AI creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy policy
  • Terms
  • RSS feed