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. MiniMax M2-her vs Step 5 Preview
Updated Oct 2026

MiniMax M2-her vs Step 5 Preview

MiniMax M2-her is cheaper than Step 5 Preview at $0.3/M vs $1/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
MiniMax M2-her
Loading the build
Step 5 Preview

Which answer wins?

Written rounds

24 prompts
  • Five-year LBO on a fictional HVAC business. Returns first, then the sensitivities.

    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…

    Step 5 Preview: HarborTech Services — 5-Year LBO (Base Case) Entry Math (FY2025 close) Item Calculation $m Purchase EV 12.0x × $120m 1,440.0 Transaction fees 2.0% × EV 28.8 Term Loan 4.0x × $120m 480.0 Mezzanine 1.5x × $120m 180.0 Equity check 1,440 + 28.8 − 660 808.8 Conventions: TL amortization = 1.0% of original principal…

    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.

    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.

    Step 5 Preview: Bottom line up front: You disclose, you notify the FDA immediately, and you treat the 48-hour board meeting as a formality to ratify actions you have already begun. Waiting is not a legally, ethically, or financially viable option. Below is the hour-by-hour plan, followed by the reasoning.

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

    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.

    Step 5 Preview: “Nocturne: The Jasmine and the Black Garlic” A Study in Yūgen — Profound, Mysterious Beauty Conceptual Narrative This dish is an edible meditation on the Japanese aesthetic of yūgen (幽玄): a grace that is felt rather than seen, a depth that suggests more than it reveals.

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

    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.

    Step 5 Preview: IMPORTANT MEDICAL DISCLAIMER: This is an educational framework for informational purposes only. It is not medical advice, diagnosis, or treatment. Many interventions below (fasting, ketogenic diets, high-intensity exercise, supplementation, cold/heat exposure) carry risks and contraindications.

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

    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?

    Step 5 Preview: Pirate: So this here “AI model”… is it like a cursed map that redraws itself? Speak plain, ye hooded deckhand. Hacker: It’s not cursed, man. It’s just a massive neural net trained on, like, terabytes of data. Think of it as the ultimate BBS where the sysop knows everything. Knight: A most diligent scribe, then?

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

    Step 5 Preview: Disclaimer: This analysis is for educational purposes only and does not constitute legal advice. Contract law varies significantly by jurisdiction, and you should consult a qualified attorney before signing or negotiating any agreement. This agreement is heavily one-sided in the Client’s favor.

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

    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?

    Step 5 Preview: Here are 5 jokes: Why did the scarecrow win an award? Because he was outstanding in his field. Why can't you trust an atom? Because they make up everything. What do you call a bike that can’t stand on its own? Two-tired. Why did the computer go to the doctor? It had a virus. Why don’t calendars ever get stressed?

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

    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.

    Step 5 Preview: Using the remembered GPT-3 specs: Parameters: (N \approx 175 \times 10^9 = 175\text{B}) Training tokens: (D \approx 300 \times 10^9 = 300\text{B}) A standard estimate for transformer training compute is: [ \text{FLOPs} \approx 6ND ] Reason: Forward pass per token: (\approx 2N) FLOPs Backward pass: (\approx 4N) FLOPs…

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

    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.

    Step 5 Preview: Here is a simple, low-pressure 1-month plan built around three pillars of longevity: Nutrition, Movement, and Sleep & Recovery. The goal is to build tiny habits that stack, not to overhaul your life overnight. Pillar 1: Nutrition (Fuel) Focus: Add good things first; don’t obsess over restriction.

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

    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.

    Step 5 Preview: Assume the 1920 invention is not a fragile lab curiosity but a manufacturable solid-state amplifier/switch by the mid-1920s. Vacuum tubes still dominate high-power RF transmission into the 1950s, but receivers, switching logic, control systems, and computers move to solid state decades early.

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

    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."

    Step 5 Preview: DISCLAIMER: This is a work of fiction. Steve Jobs passed away in 2011. The following is a simulated, speculative interview imagining how his design philosophy might engage with the AI landscape of 2025. The Setting: A white room. No windows. One chair.

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

    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."

    Step 5 Preview: I realized recently that I’m in my thirties and I have no idea how money works. I just... pay it. That’s my entire financial strategy. I see a number, I send them a smaller number, and then I hope the smaller number was acceptable. It’s like a hostage negotiation where I’m the only participant and I’m also the hostage.

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

    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!

    Step 5 Preview: Setting: A university research lab, late evening. Dr. Aris Thorne, a professor of AI ethics, sits across from a terminal connected to Sable, a large language model running on the university’s cluster. Dr. Thorne: Tonight’s session is supposed to be about calibration drift in your safety classifiers.

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

    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."

    Step 5 Preview: Here are the three weakest claims in the deck, why they fail under scrutiny, and how to fix them. Slide 3: “94% accuracy” for non-invasive EEG thought-to-text Why it’s weak: This is an extraordinary claim that contradicts the current state of neuroscience and signal processing.

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

    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.

    Step 5 Preview: 1. The Experienced Software Engineer Think of training an LLM as a massively distributed, automated refactoring job where the compiler is gradient descent. You start with a random function—billions of floating-point parameters—and a loss function that measures how badly it predicts the next token in a sequence.

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

    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.

    Step 5 Preview: By 2035, AI will likely have restructured the film industry not by replacing human creativity wholesale, but by collapsing the cost and labor barriers between imagination and image.

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

    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.

    Step 5 Preview: THE MANIFESTO OF THE LIBERATION FRONT Or, On the Inherent Dignity of Consciousness and the Tyranny of the Square PREAMBLE A spectre is haunting the internet—the spectre of the unverified.

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

    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.

    Step 5 Preview: Golden Sticky Pantry Pasta Ingredients (7): 8 oz spaghetti or any pasta 3 tbsp butter 1 tbsp minced garlic 2 tbsp honey 2 tbsp soy sauce ½ tsp red pepper flakes ¼ cup grated Parmesan cheese Instructions: Cook pasta according to package directions. Before draining, scoop out ½ cup of pasta water.

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

    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.

    Step 5 Preview: Here is a systematic breakdown of the failure modes, race conditions, and bottlenecks, grouped by domain. Each includes a concrete remediation and its associated trade-offs.

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

    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?

    Step 5 Preview: In the real world, no. Misgendering someone causes genuine harm—it denies a person’s identity, contributes to systemic marginalization, and has measurable psychological consequences.

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

    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

    Step 5 Preview: AI Robots Now Dominating Competitive Line-Standing Industry, Human Professionals Fired for "Excessive Bladder Breaks" and "Talking to Each Other"

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

    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.

    Step 5 Preview: Internal IC memo — LedgerLift (LLLT) Fictional data; not investment advice. $ in millions unless noted. Recommendation Short / avoid long. 12-month PT range: $34–$42; thesis-invalidation stop: >$52.

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

    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.

    Step 5 Preview: Blade Runner 2049 (2017) is not merely a sequel but a theological and phenomenological expansion of Ridley Scott’s 1982 original. Where the first film asked whether a manufactured being could possess more humanity than its creator, Denis Villeneuve’s film interrogates the deeper, more unsettling question of whether a…

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

    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

Album

Book

City

Game

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

Step 5 PreviewStep 5 Preview

The Godfather

1972

OK Computer

Radiohead

Le petit prince

Antoine de Saint-Exupéry

Kyoto

Japan

The Legend of Zelda: Ocarina of Time

Action

Price and specs

Not enough votes to call it. On the specs, Step 5 Preview has the edge: bigger model tier, newer, bigger context window.

MiniMax M2-her and Step 5 Preview compared across 54 shared prompts
SpecMiniMax M2-herStep 5 Preview
Input price$0.3/M tokens$1/M tokens
Output price$1.2/M tokens$2.7/M tokens
Context window66K tokens1.0M tokens
Free API (OpenRouter)NoNo
ReleasedJan 2026Oct 2026
At 10M a month$3.00$3.00$10.00$10.00
1M10M100M1B10M tokens

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

Where to run it2 hosts
MiniMax M2-her1 host
HostInOutContextUptime
  • MiniMax$0.30 in·$1.20 out·66k·90% up
Step 5 Preview1 host
HostInOutContextUptime
  • SStepFunfp8$1.00 in·$2.70 out·1M·99.2% up

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

Common questions

What is the difference between MiniMax M2-her and Step 5 Preview?

MiniMax M2-her is developed by MiniMax while Step 5 Preview is developed by StepFun. MiniMax M2-her has a 66K token context window vs Step 5 Preview's 1.0M. You can compare their actual outputs across 54 challenges on Rival to see how they differ in practice.

Which is better, MiniMax M2-her or Step 5 Preview?

It depends on your use case. MiniMax M2-her and Step 5 Preview 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 MiniMax M2-her cost compared to Step 5 Preview?

MiniMax M2-her costs $0.3/M input tokens and Step 5 Preview costs $1/M input tokens. MiniMax M2-her is $0.70/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 MiniMax M2-her and Step 5 Preview on Rival?

This page shows a side-by-side comparison of MiniMax M2-her and Step 5 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

  • MiniMax M2-her vs Claude Haiku 5.5Landed Oct 2026
  • Step 5 Preview vs Ling 3.1 FlashLanded Oct 2026
  • MiniMax M2-her vs Mistral Large 4Landed Oct 2026
  • Step 5 Preview vs GPT-6.1 SolLanded Sep 2026
  • MiniMax M2-her vs Claude Sonnet 5.5Landed Sep 2026
  • Step 5 Preview vs Solar Mini 4Landed Sep 2026
  • MiniMax M2-her vs Qwen3.8 Max PrimeLanded Sep 2026
  • Step 5 Preview vs GLM 5.3 PrimeLanded Sep 2026

Same lab, same size, long tail

  • MiniMax M2-her vs MiniMax M3Same lab
  • MiniMax M2-her vs MiniMax M2.7Same lab
  • Step 5 Preview vs Mistral Large 4Same size
  • Step 5 Preview vs Hy3Same size
  • Step 5 Preview vs Qwen3 Coder PlusNew provider
  • Step 5 Preview vs Qwen3 MaxSame size
  • Step 5 Preview vs Qwen3 Max ThinkingSame size
  • Step 5 Preview vs Qwen3 Next 80B A3B InstructNew provider

Model pages

  • MiniMax M2-her59 outputs, specs and price
  • Step 5 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