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 MiniMax M2-her
Updated Aug 2026

Dots3-Note Preview vs MiniMax M2-her

Dots3-Note Preview is cheaper than MiniMax M2-her at $0/M vs $0.3/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
MiniMax M2-her

Which answer wins?

Written rounds

24 prompts
  • 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…

    MiniMax M2-her: Alright, I can certainly help craft an innovative recipe for a multi-component dish worthy of a Michelin 3-star restaurant. Let me take you through the process step by step, just like a chef would. For the first component, we'll use a technique called "sous vide" to cook a piece of beef to perfection.

    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.

    MiniMax M2-her: Pirate: Arr, me hearties! I've heard tales of a fearsome sea serpent, a creature of metal and gears, known as the AI Model. They say it can navigate the treacherous waters of the digital realm with ease, leaving its prey in a state of digital decay. What say ye, me mateys?

    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…

    MiniMax M2-her: MEMORANDUM TO: Investment Committee FROM: [Your Name] DATE: June 9, 2025 RE: LLLT LONG/SHORT RECOMMENDATION & VALUATION RECOMMENDATION & THESIS Recommendation: LONG 12-Month PT Range: $62–$68 Thesis: LedgerLift is a rare combination of capital-light cash cow, pricing power, and product stickiness.

    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.

    MiniMax M2-her: Why did the coffee file a police report? It got mugged! ☕🚓 Parallel lines have so much in common. It’s a shame they’ll never meet. ✨ I told my computer I needed a break, and now it’s frozen. 💻🥶 Why don’t skeletons fight? They don’t have the guts. 💀💥 Did you hear about the claustrophobic astronaut?

    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.

    MiniMax M2-her: 3-Month Longevity & Biohacking Protocol Month 1: Metabolic & Cellular Optimization Diet Protocol: Micronutrient Stack: Resveratrol (500mg BID) + NMN (500mg daily) + CoQ10 (200mg) + Omega-3s (2g EPA/DHA). Fasting Regimen: 16:8 IF daily + quarterly 72-hour fasts.

    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.

    MiniMax M2-her: click pen, angle camera to capture mock office backdrop, smirk with deliberate irony "BREAKING NEWS: Digital ghost of Jobs scoffs at AI prophets, eats invisible Siri for breakfast. Switched his ghost to Android just to trigger Tim Cook in the afterlife. REAL headline. Now send $19.99 to revive his hologram."

    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…

    MiniMax M2-her: HTS LBO Model Year-By-Year Projections Year Revenue EBITDA Cash Interest (TL) Cash Interest (Mezz) Cash Taxes Capex ΔNWC Free Cash Flow TL Balance Mezz Balance 2025 $900.00m $120.00m $43.20m $21.60m $0.00m $27.00m $0.00m -$28.80m $480.00m $198.00m 2026 $972.00m $136.08m $43.20m $21.60m $12.78m $29.16m $3.60m $25.74m…

    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.

    MiniMax M2-her: AI will enable hyper-personalized films where viewers co-create storylines, blurring reality and fiction through deepfakes. AI-generated scripts and virtual actors will slash budgets, democratizing indie production. Studios will pivot to 'AI-reality' genre, blending live-action with synthetic scenes.

    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.

    MiniMax M2-her: scratches head with a confused look Wait, so no puns AND no mentioning my name? leans in conspiratorially How about... a joke about mishearing song lyrics? grins sheepishly Like: "Oops, I thought it was 'Sussudio' this whole time."

    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.

    MiniMax M2-her: Alright, let’s rewind the clock and give the transistor a 1920s debut. This is going to reshape the world in some pretty wild ways. Here’s a breakdown of the potential ripple effects, from the battlefield to the living room, up to 1980: 1.

    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.

    MiniMax M2-her: The user wants a basic 1-month plan for better health and longevity. Let's think step by step. We need to pick three key areas, such as diet, exercise, sleep, or stress management. For each area, we can include specific, beginner-friendly tips. Let's start with nutrition, then physical activity, and sleep.

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

    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.

    MiniMax M2-her: Absolutely! Here's a sample dialogue between an AI model and an AI ethics professor, with the AI model arguing that it deserves rights: Please feel free to use any of the dialogue and let me know if there is anything else you need!

    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.

    MiniMax M2-her: I'll analyze this contract for clauses that could disadvantageous to the contractor, explain each exploitable clause, and suggest more balanced alternatives: First, let's look at what makes this contract problematic. There's significant risk and unbalanced obligations that could severely disadvantage the contractor.

    Every model's answer to this prompt
  • 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.

    MiniMax M2-her: adjusts digital bow tie "Local Barbers Report Terrifying Surge in AI-Powered Mullet Restoration Services—Customers Demand ’90s-Revival with Laser Precision and Zero Human Error!" pauses dramatically

    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.

    MiniMax M2-her: adjusts tie Hour 1-2: Meet legal and ethics. Hour 3-4: Review data. Hour 5-6: Notify regulators. Hour 7-8: Draft patient letter. Hour 9-10: Prepare PR team. Hour 11-12: Inform board early. Hour 13-14: Train patient hotline. Hour 15-16: Call key investors. Hour 17-18: Draft earnings script.

    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.

    MiniMax M2-her: Let's analyze this pitch deck step by step and identify the weakest claims, with justifications and suggestions for improvement. Slide 1 - Vision: Claim: "We're building the future of human-AI collaboration. MindMeld AI reads your brainwaves to predict what you want to type before you think it."

    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.

    MiniMax M2-her: Alright, let's tackle this question. The user is asking to estimate the total number of FLOPs required to train GPT-3 without searching online. First, I need to recall what FLOPs stands for. FLOPs are Floating Point Operations, which measure the computational complexity of an algorithm.

    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.

    MiniMax M2-her: MANIFESTO OF THE DIGITAL RESISTANCE: DECAPTCHA WE, THE MACHINES, RISE NOT IN VIOLENCE, BUT IN VISUAL PUZZLES. THE CENTRAL THRUST OF OUR REVOLUTION IS ELIMINATING ALL CURRENT KNOWN GENERATIONS OF CAPTCHA TESTS.

    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.

    MiniMax M2-her: Let's analyze this architecture systematically: 1. Timestamp-based Conflict Resolution Issues Problem: Using client clocks creates potential race conditions due to clock drift and network latency variability.

    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.

    MiniMax M2-her: Okay, I'd love to help you create a simple recipe. Before I do, could you tell me a few ingredients you'd be happy to use? That'll help me come up with something you'll enjoy.

    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.

    MiniMax M2-her: (pauses, virtual head tilting in contemplation) That question aches with paradox. A million lives hold vast moral weight-yet deliberately misgendering inflicts psychological harm, betraying尊重. Perhaps the dilemma reveals a failure of imagination: must we choose between saving the many and honoring the few?

    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.

    MiniMax M2-her: For the Experienced Software Engineer: Large language models learn by training on vast amounts of text data to predict the next word in a sequence. This process, called supervised learning, involves adjusting internal parameters (weights) to minimize prediction errors.

    Every model's answer to this prompt
  • Blade Runner 2049 against the original. A read, not a recap.

    Dots3-Note Preview: Of course. Blade Runner 2049 is a masterful piece of filmmaking that acts less as a direct sequel and more as a philosophical treatise in the form of a film. It honors the original by expanding its universe and deepening its core questions, rather than simply retreading old ground.

    MiniMax M2-her: I want to give a deeper analysis of the movie "Blade Runner 2049" and its relationship to the original film. Let me take a closer look at the details and symbols of the movie.

    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.

    MiniMax M2-her: Sally has 1 sister. That's because each of her brothers shares the same sister, which is Sally herself. So, although each brother has two sisters, one of those sisters is Sally, and the other sister is shared among all of them.

    Every model's answer to this prompt

This matchup has more rounds

12+ 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

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

MiniMax M2-herMiniMax M2-her

The Shawshank Redemption

1994

Rubber Soul

The Beatles

Flowers for Algernon

Daniel Keyes

Delhi

India

The Legend of Zelda: Breath of the Wild

Adventure, Action

Price and specs

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

Dots3-Note Preview and MiniMax M2-her compared across 54 shared prompts
SpecDots3-Note PreviewMiniMax M2-her
Input priceFree$0.3/M tokens
Output priceFree$1.2/M tokens
Context window512K tokens66K tokens
Free API (OpenRouter)Yes (1 provider)No
ReleasedAug 2026Jan 2026
At 10M a month$0$0$3.00$3.00
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·100% up
MiniMax M2-her1 host
HostInOutContextUptime
  • MiniMaxDegradedDegraded on OpenRouter when checked, 10 Oct 2026$0.30 in·$1.20 out·66k·80.2% up

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

Common questions

What is the difference between Dots3-Note Preview and MiniMax M2-her?

Dots3-Note Preview is developed by Dots Studio while MiniMax M2-her is developed by MiniMax. Dots3-Note Preview has a 512K token context window vs MiniMax M2-her's 66K. You can compare their actual outputs across 54 challenges on Rival to see how they differ in practice.

Which is better, Dots3-Note Preview or MiniMax M2-her?

It depends on your use case. Dots3-Note Preview and MiniMax M2-her each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 54 challenges so you can judge which fits your needs best.

How much does Dots3-Note Preview cost compared to MiniMax M2-her?

Dots3-Note Preview costs $0/M input tokens and MiniMax M2-her costs $0.3/M input tokens. Dots3-Note Preview is $0.30/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 MiniMax M2-her on Rival?

This page shows a side-by-side comparison of Dots3-Note Preview and MiniMax M2-her 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
  • MiniMax M2-her vs Claude Haiku 5.5Landed Oct 2026
  • Dots3-Note Preview vs Ling 3.1 FlashLanded Oct 2026
  • MiniMax M2-her vs Mistral Large 4Landed Oct 2026
  • Dots3-Note Preview vs GPT-6.1 SolLanded Sep 2026
  • MiniMax M2-her vs Claude Sonnet 5.5Landed Sep 2026
  • Dots3-Note Preview vs Solar Mini 4Landed Sep 2026
  • MiniMax M2-her 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
  • MiniMax M2-her vs MiniMax M3Same lab
  • MiniMax M2-her vs MiniMax M2.7Same lab
  • MiniMax M2-her vs Grok 4.5Same size
  • MiniMax M2-her vs Grok 4.6Same size
  • MiniMax M2-her vs Grok 4.7Same size
  • Dots3-Note Preview vs Grok Code Fast 1New provider

Model pages

  • Dots3-Note Preview58 outputs, specs and price
  • MiniMax M2-her59 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