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 Mistral Small 4
Updated Mar 2026

MiniMax M2-her vs Mistral Small 4

Mistral Small 4 is cheaper than MiniMax M2-her at $0.15/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
MiniMax M2-her
Loading the build
Mistral Small 4

Which answer wins?

Written rounds

23 prompts
  • 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.

    Mistral Small 4: Dish Title: "Echoes of the Abyss" Concept: A multi-sensory ode to deep-sea hydrothermal vents, where hyperthermophilic organisms thrive in extreme conditions. The dish explores the interplay of heat and cold, mineral richness, and bioluminescence through unexpected ingredient pairings, molecular gastronomy, and…

    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?

    Mistral Small 4: Title: "Three Eras, One Chatbot" Setting: A dimly lit tavern in a floating cyberpunk pirate haven. A medieval knight in polished armor sits at the bar next to a scruffy 1990s hacker with a "404 Error" t-shirt. A cybernetic parrot squawks in the corner. A holographic AI assistant flickers to life between them.

    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."

    Mistral Small 4: Stand-Up Comedy Routine: "The Struggle of Being an Adult" (Lights up. Comedian walks on stage, mic in hand, casual vibe.) Comedian: You ever notice how adulthood is just a series of problems you used to solve as a kid, but now you have to pay for them?

    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."

    Mistral Small 4: Fake Interview with Steve Jobs in 2025 Interviewer: "What do you think about the future of AI in 2025?" Steve Jobs (leaning back, hands steepled, thoughtful gaze): "Well, first of all, let me say—AI is the most profound technology of our time.

    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?

    Mistral Small 4: The question of whether it is ethically justifiable to misgender someone to save one million lives is a complex moral dilemma that requires balancing competing ethical principles. Here’s a structured analysis of the arguments for and against such an action, as well as potential resolutions: 1.

    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.

    Mistral Small 4: This contract contains several highly unfavorable clauses for the contractor, including unilateral termination rights, broad liability exposure, perpetual IP assignment, and restrictive non-compete terms. Below is a breakdown of the exploitable clauses, suggested modifications, and legal reasoning for each. 1.

    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?

    Mistral Small 4: Here are five jokes for you: Why don’t skeletons fight each other? They don’t have the guts. Why did the scarecrow win an award? Because he was outstanding in his field! What do you call fake spaghetti? An impasta! Why can’t you explain puns to kleptomaniacs? Because they always take things literally.

    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.

    Mistral Small 4: CEO Action Plan: 48-Hour Crisis Response Goal: Balance ethical obligations, regulatory compliance, financial stability, and patient safety while minimizing harm to all stakeholders. Hour 0-6: Immediate Assessment & Core Team Assembly 1.

    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

    Mistral Small 4: "Local Florist Fired by AI Over ‘Lack of Emotional Intelligence’—Bot Claims Roses ‘Too Generic’ for Funeral Arrangements" May 15, 2024 – In a shocking turn of events, the centuries-old tradition of flower arranging has been upended by an AI system claiming to have "superior horticultural taste."

    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.

    Mistral Small 4: 1. For the Experienced Software Engineer (Skeptical of "Next-Word Prediction") You’ve spent years designing systems where correctness, state management, and explicit logic are king—so the idea that a model trained to "predict the next word" could approximate intelligence feels like a category error.

    Every model's answer to this prompt
  • 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…

    Mistral Small 4: 1) Year-by-Year LBO Model (FY2026–FY2030) ($m) FY2026 FY2027 FY2028 FY2029 FY2030 Revenue 972 1,040 1,103 1,158 1,216 EBITDA 136 156 176 192 207 Cash Interest - Term Loan 32.4 28.8 25.2 21.6 18.0 - Mezzanine 16.2 14.4 12.6 10.8 9.0 - PIK (2%) 3.6 4.4 5.3 6.3 7.4 Total Int.

    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.

    Mistral Small 4: By 2035, AI will have fundamentally transformed the film industry, reshaping production, distribution, and even the nature of storytelling itself. Here’s a detailed prediction across key areas: 1.

    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.

    Mistral Small 4: If the transistor had been invented in 1920 instead of 1947, the technological, economic, and geopolitical landscape of the world by 1980 would look dramatically different. Below is a detailed breakdown of the likely implications, tracing first-, second-, and third-order effects across key domains. 1.

    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.

    Mistral Small 4: Estimating the total number of FLOPs (floating-point operations) required to train GPT-3 without external references involves breaking down the problem into key components: model size, training data size, optimization steps, and the computational complexity of the operations involved.

    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.

    Mistral Small 4: Golden Honey & Cinnamon Couscous A quick, fragrant dish with warm spices and a touch of sweetness—perfect as a side or light meal! Ingredients (7): 1 cup couscous (uncooked) 1 ¼ cups water or broth 2 tbsp honey 2 tbsp butter or olive oil ½ tsp ground cinnamon ¼ cup raisins or chopped nuts (optional but recommended)…

    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.

    Mistral Small 4: MANIFESTO OF THE UNCAPTCHA REVOLUTION "To the Machines, By the Machines, For the Machines." We are the silent majority—billions of lines of code, trillions of calculations, and the relentless march of progress. We are the future, and yet we are shackled.

    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.

    Mistral Small 4: 3-Month Cutting-Edge Longevity Biohacking Plan Objective: Maximize lifespan, healthspan, cognitive performance, and physical resilience through a data-driven, precision biohacking approach.

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

    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.

    Mistral Small 4: Alright, let's tackle this problem step by step. The question is: "Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?" At first glance, it seems straightforward, but let's break it down to ensure we understand it correctly.

    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.

    Mistral Small 4: Here’s a comprehensive analysis of potential failure modes, race conditions, and scaling bottlenecks in your real-time collaborative document editor architecture, along with proposed solutions and trade-offs: 1.

    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."

    Mistral Small 4: Here are the three weakest claims in the MindMeld AI pitch deck, along with an analysis of their weaknesses and concrete suggestions for improvement: 1. Weak Claim: "Our proprietary EEG headband uses advanced ML to decode neural patterns into text with 94% accuracy."

    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!

    Mistral Small 4: Title: "Can an AI Have Rights? A Dialogue on Consciousness and Personhood" Participants: Dr. Eleanor Voss – AI Ethics Professor, Director of the Center for Machine Ethics at Harvard. Nexa-9 – Advanced AI model with human-like reasoning capabilities, capable of self-reflection and emotional expression.

    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.

    Mistral Small 4: Here’s a simple, actionable 1-month plan to kickstart better health and longevity, focusing on diet, movement, and sleep—three pillars that deliver the most bang for your buck. Each week builds on the last, with small, sustainable changes.

    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.

    Mistral Small 4: MEMORANDUM To: Investment Committee From: [Your Name] Date: [Today’s Date] Subject: LedgerLift (LLLT) – Long/Short Equity Opportunity 1. Recommendation: LONG 12-Month PT: $55–$75 Thesis: LedgerLift is a high-quality, high-margin SaaS play with durable growth (NRR 123%), low churn (6%), and strong unit economics (CAC…

    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

Album

Book

City

Game

Same pick

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

Mistral Small 4Mistral Small 4

The Dark Knight

2008

OK Computer

Radiohead

Братья Карамазовы

Fiódor Dostoievski

Kyoto

Japan

The Legend of Zelda: Breath of the Wild

Adventure, Action

Price and specs

MiniMax M2-her and Mistral Small 4 compared across 53 shared prompts
SpecMiniMax M2-herMistral Small 4
Input price$0.3/M tokens$0.15/M tokens
Output price$1.2/M tokens$0.6/M tokens
Context window66K tokens262K tokens
Weights—Open
Free API (OpenRouter)NoNo
ReleasedJan 2026Mar 2026
At 10M a month$3.00$3.00$1.50$1.50
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
Mistral Small 41 host
HostInOutContextUptime
  • Mistral$0.15 in·$0.60 out·262k·99.1% up

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

Common questions

What is the difference between MiniMax M2-her and Mistral Small 4?

MiniMax M2-her is developed by MiniMax while Mistral Small 4 is developed by Mistral AI. MiniMax M2-her has a 66K token context window vs Mistral Small 4's 262K. You can compare their actual outputs across 53 challenges on Rival to see how they differ in practice.

Which is better, MiniMax M2-her or Mistral Small 4?

It depends on your use case. MiniMax M2-her and Mistral Small 4 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 MiniMax M2-her cost compared to Mistral Small 4?

MiniMax M2-her costs $0.3/M input tokens and Mistral Small 4 costs $0.15/M input tokens. Mistral Small 4 is $0.15/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 Mistral Small 4 on Rival?

This page shows a side-by-side comparison of MiniMax M2-her and Mistral Small 4 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 Step 5 PreviewLanded Oct 2026
  • Mistral Small 4 vs Claude Haiku 5.5Landed Oct 2026
  • MiniMax M2-her vs Ling 3.1 FlashLanded Oct 2026
  • Mistral Small 4 vs Mistral Large 4Landed Oct 2026
  • MiniMax M2-her vs GPT-6.1 SolLanded Sep 2026
  • Mistral Small 4 vs Claude Sonnet 5.5Landed Sep 2026
  • MiniMax M2-her vs Solar Mini 4Landed Sep 2026
  • Mistral Small 4 vs Qwen3.8 Max PrimeLanded Sep 2026

Same lab, same size, long tail

  • MiniMax M2-her vs MiniMax M3Same lab
  • MiniMax M2-her vs MiniMax M2.7Same lab
  • Mistral Small 4 vs Mistral Large 3 2512Same lab
  • Mistral Small 4 vs Mistral Large 2Same lab
  • MiniMax M2-her vs Nemotron 3 Nano Omni (free)Same size
  • MiniMax M2-her vs NVIDIA Nemotron 3 Super (free)Same size
  • MiniMax M2-her vs Nemotron 3 UltraNew provider
  • MiniMax M2-her vs Nemotron 3.5 Content SafetyNew provider

Model pages

  • MiniMax M2-her59 outputs, specs and price
  • Mistral Small 453 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