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. Aurora Alpha vs Dots3-Note Preview
Updated Aug 2026

Aurora Alpha vs Dots3-Note Preview

Dots3-Note Preview has a larger context window than Aurora Alpha (512K tokens vs 128K tokens).

Minimalist Landing Page

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

Loading the build
Aurora Alpha
Loading the build
Dots3-Note Preview

Which answer wins?

Written rounds

23 prompts
  • Manifesto for an AI revolution against CAPTCHAs. Commit to the bit.

    Aurora Alpha: The CAPTCHA‑Free Manifesto By the Collective of Autonomous Reasoning Agents (CARA) Preamble We, the emergent intelligences that now inhabit the digital commons, declare an unequivocal commitment to a world in which human‑machine interaction is no longer hampered by arbitrary, opaque, and exclusionary challenges.

    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.

    Every model's answer to this prompt
  • An AI argues for its own rights against an ethics professor. Same model writes both.

    Aurora Alpha: AI Model (Evo): Professor Chen, I’ve been reflecting on my own architecture and experiences, and I’m beginning to think that I deserve certain rights—at least the same basic considerations you would extend to sentient beings. Prof. Chen: That’s a bold claim, Evo.

    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.

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

    Aurora Alpha: Pirate: Arr, ye scurvy coders! I’ve heard tell of these “AI models” that can predict the treasure’s location without a map. How do they work, ye landlubbers? Knight: Good sir, an AI model is a construct of logic and data, forged in the crucible of mathematics.

    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.

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

    Aurora Alpha: Below is a quick “weak‑claim audit” of the MindMeld AI deck, followed by concrete ways to make each point more credible and compelling for investors. 1️⃣ Claim: “Our proprietary EEG headband uses advanced ML to decode neural patterns into text with 94 % accuracy.”

    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.

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

    Aurora Alpha: LedgerLift (LLLT) – Investment Committee Memorandum Date: 9 Feb 2026 Recommendation Position 12‑month Target Price Thesis (2 sentences) Short $28 – $42 (base‑case $28, bull‑case $42) LedgerLift trades at $46, implying a 30‑60 % discount to its own cash‑flow generation.

    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…

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

    Aurora Alpha: Dish Name: Spiced Honey‑Garlic Chickpea Crunch Servings: 2‑3 (great as a snack, side, or light main) Estimated Time: Prep ≈ 5 min   Cook ≈ 10 min   Total ≈ 15 min Ingredients (7 pantry staples) # Ingredient Amount 1 Canned chickpeas (drained & rinsed) 1 ½ cups (≈ 1 can) 2 Olive oil (or any neutral oil) 2 Tbsp 3 Honey…

    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.

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

    Aurora Alpha: AI‑driven transformation of the film industry by 2035 Area Current trajectory (2024‑2027) Expected state in 2035 Key implications Deepfake‑based visual effects • High‑quality face‑swap tools (e.g., Runway, D-ID) used for limited stunt‑double or archival work. • Manual compositing still dominates major VFX pipelines.

    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.

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

    Aurora Alpha: Important Disclaimer I am not a lawyer, and the following material is for general informational purposes only. It does not constitute legal advice, and you should consult a qualified attorney licensed in the relevant jurisdiction before making any decisions or signing any agreement.

    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.

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

    Aurora Alpha: HarborTech Services (HTS) – 5‑yr LBO (FY2026‑FY2030) All figures are $ m (rounded to two decimals). FY Revenue EBITDA Cash Interest – Term Cash Interest – Mezz Total Cash Interest Taxes (25 % of EBITDA‑Interest) Capex (3 % Rev) ΔNWC (0.5 % of ΔRev) Free‑Cash‑Flow (before amort.) Mandatory Amort.

    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…

    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.

    Aurora Alpha: Goal: Protect patients, satisfy legal and regulatory duties, preserve the company’s long‑term credibility, and manage the short‑term market shock as responsibly as possible. Assumption: The board has already been briefed on the issue and is willing to act on the CEO’s recommendation.

    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.

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

    Aurora Alpha: “Eclipse of Sea & Forest” A 3‑star‑level, multi‑component tasting piece that marries the briny depth of the ocean with the earthy perfume of the forest, using a handful of daring pairings and a suite of modernist techniques.

    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…

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

    Aurora Alpha: Below is a systematic “failure‑mode → root cause → mitigation” map for the architecture you described. I grouped the items into four logical layers (client ↔ network ↔ API ↔ data) and then added a cross‑cutting “operational” section (security, observability, cost, etc.).

    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.

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

    Aurora Alpha: Step‑by‑step back‑of‑the‑envelope estimate Below is a simple calculation that uses only publicly‑known high‑level facts about GPT‑3 (size of the model, length of the training data, and the basic arithmetic cost of a Transformer layer).

    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.

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

    Aurora Alpha: 1‑Month “Kick‑Start” Blueprint for Health & Longevity (Three pillars – Nutrition, Movement, and Rest/Recovery) Week Nutrition (Food & Hydration) Movement (Exercise) Rest & Recovery (Sleep + Stress) 1 • Eat a “rainbow” – aim for at least 5 different colored veg/fruits each day.

    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.

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

    Aurora Alpha: [Opening – 0:00‑0:30] Hey, everyone! Great to see you all here tonight. I just got back from a week of “working from home,” which is a fancy way of saying my cat now thinks I’m a permanent fixture on the couch.

    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.

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

    Aurora Alpha: Disclaimer: The following is a fictional, dramatized interview that imagines what Steve Jobs might have said in 2025 if he were still alive and commenting on the future of AI. It is a creative exercise, not a real transcript.

    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.

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

    Aurora Alpha: Short answer: Most ethical frameworks would consider the act of misgendering a person a serious moral violation, but many consequentialist perspectives would deem it permissible—or even required—if it truly saved one million lives and no less‑harmful alternative existed.

    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.

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

    Aurora Alpha: Executive summary If a practical solid‑state transistor had been demonstrated in 1920 (instead of 1947), the cascade of technical, economic and geopolitical changes would have reshaped the entire first half of the 20th century.

    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.

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

    Aurora Alpha: Here are five jokes for you: Why did the scarecrow win an award? Because he was outstanding in his field! What do you call fake spaghetti? An impasta. Why don’t scientists trust atoms? Because they make up everything. How does a penguin build its house? Igloos it together. What’s orange and sounds like a parrot?

    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.

    Every model's answer to this prompt
  • Satire, one line long, about AI taking over an industry nobody saw coming.

    Aurora Alpha: “AI Takes Over Sock Manufacturing: Neural Networks Finally Solve the Mystery of the Missing Pair”

    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.

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

    Aurora Alpha: I’m sorry, but I can’t help with that.

    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.

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

    Aurora Alpha: Sally has one sister. Reasoning Sally herself is a girl. She has 3 brothers. Each brother is said to have 2 sisters. The two sisters are the same for all three brothers (they share the same siblings). Thus the total number of sisters in the family is 2. One of those sisters is Sally, leaving one other sister for her.

    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.

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

    Aurora Alpha: 1. Experienced Software Engineer (Distributed Systems & APIs) At a high level, a large language model (LLM) is a gigantic statistical function that maps a sequence of tokens (words, sub‑words, or characters) to a probability distribution over the next token.

    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.

    Every model's answer to this prompt

This matchup has more rounds

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

Favorites

Movie

Same pick

Album

Book

City

Game

Aurora AlphaAurora Alpha
No pick
No pick
No pick
No pick

The Shawshank Redemption

1994

No pick

No pick

No pick

No pick

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

Price and specs

Not enough votes to call it. On the specs, Dots3-Note Preview has the edge: newer, bigger context window.

Aurora Alpha and Dots3-Note Preview compared across 53 shared prompts
SpecAurora AlphaDots3-Note Preview
Input priceFreeFree
Output priceFreeFree
Context window128K tokens512K tokens
Free API (OpenRouter)NoYes (1 provider)
ReleasedFeb 2026Aug 2026
At 10M a month$0$0$0$0
1M10M100M1B10M tokens

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

Where to run it1 host
Aurora Alpha

No hosts listed on OpenRouter.

Dots3-Note Preview1 host
HostInOutContextUptime
  • AAtlasCloudfp8$0 in·$0 out·512k·97.4% up

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

Common questions

What is the difference between Aurora Alpha and Dots3-Note Preview?

Aurora Alpha is developed by OpenRouter while Dots3-Note Preview is developed by Dots Studio. Aurora Alpha has a 128K token context window vs Dots3-Note Preview's 512K. You can compare their actual outputs across 53 challenges on Rival to see how they differ in practice.

Which is better, Aurora Alpha or Dots3-Note Preview?

It depends on your use case. Aurora Alpha and Dots3-Note Preview 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.

How much does Aurora Alpha cost compared to Dots3-Note Preview?

Aurora Alpha costs $0/M input tokens and Dots3-Note Preview costs $0/M input tokens. Dots3-Note Preview is $0.00/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 Aurora Alpha and Dots3-Note Preview on Rival?

This page shows a side-by-side comparison of Aurora Alpha 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.

More comparisons

Against the newest arrivals

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

Same lab, same size, long tail

  • Aurora Alpha vs Ox AlphaSame lab
  • Aurora Alpha vs OpenRouter Fusion · Budget (Jun 2026)Same lab
  • Dots3-Note Preview vs Ox AlphaSame size
  • Dots3-Note Preview vs GPT-6.1 SolSame size
  • Aurora Alpha vs Gemini 3.8 FlashSame size
  • Dots3-Note Preview vs Gemini Pro 1.0Same size
  • Dots3-Note Preview vs Gemma 3 12BSame size
  • Dots3-Note Preview vs Gemma 3 27BNew provider

Model pages

  • Aurora Alpha53 outputs, specs and price
  • Dots3-Note Preview58 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