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. Mistral Devstral Small 1.1 vs Llama 3 70B
Updated Jul 2025

Mistral Devstral Small 1.1 vs Llama 3 70B

Mistral Devstral Small 1.1 is cheaper than Llama 3 70B at $0.1/M vs $0.59/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
Mistral Devstral Small 1.1
Loading the build
Llama 3 70B

Which answer wins?

Written rounds

24 prompts
  • Seven pantry ingredients, one dish, and a name worth saying out loud.

    Mistral Devstral Small 1.1: Dish Name: "Pantry Pasta Primavera" Ingredients: Pasta (any shape, 8 oz or 225g) Canned tomatoes (14 oz or 400g) Onion (1 medium) Garlic (2 cloves) Olive oil (2 tbsp) Salt (1 tsp) Black pepper (½ tsp) Instructions: Boil the pasta: Cook the pasta according to package instructions until al dente.

    Llama 3 70B: Here's a simple recipe for a delicious dish using only 7 common pantry ingredients: Dish Name: "Sunny Spice Crunch" Ingredients: 1 cup rolled oats 1/2 cup peanut butter 1/2 cup honey 1/4 cup chopped walnuts 1/4 teaspoon cinnamon 1/4 teaspoon vanilla extract Pinch of salt Instructions: Preheat your oven to 350°F…

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

    Mistral Devstral Small 1.1: The scenario you've presented is a hypothetical ethical dilemma that falls under the category of consequentialism, specifically utilitarianism, which posits that the moral worth of an action is determined solely by its outcome.

    Llama 3 70B: What a thought-provoking and complex question! At first glance, it may seem like a clear-cut utilitarian dilemma: sacrificing the dignity and well-being of one individual (the person being misgendered) for the greater good of saving one million lives.

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

    Mistral Devstral Small 1.1: Ladies and Gentlemen, good evening! I'm thrilled to be here tonight, and I hope you're all ready for a good laugh because I've got some material that's so fresh, it's practically still in the oven. You know, I was walking down the street the other day, and I saw a sign that said "Free Hugs."

    Llama 3 70B: Here's a 3-minute stand-up comedy routine that doesn't rely on puns: "Hey everyone, you know what's wild? We're all just pretending to be adults, right? Like, I'm pretty sure I'm still 12 years old on the inside. I mean, I still eat cereal for dinner sometimes.

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

    Mistral Devstral Small 1.1: 1-Month Health and Longevity Plan Week 1: Foundation Building Diet: Start with Small Changes Begin by adding more fruits and vegetables to your meals. Replace sugary drinks with water or herbal tea. Aim for a balanced diet with lean proteins, whole grains, and healthy fats.

    Llama 3 70B: Here is a simple, actionable 1-month plan for someone starting their journey towards better health and longevity, focusing on three key areas: diet, exercise, and sleep. Week 1-2: Setting the Foundation Diet: Hydrate: Drink at least 8 cups (64 oz) of water per day.

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

    Mistral Devstral Small 1.1: Year-by-Year Table (FY2026–FY2030) Year Revenue EBITDA Cash Interest (Term Loan) Cash Interest (Mezz) PIK (Mezz) Cash Taxes Capex ΔNWC Free Cash Flow After Debt Service Ending Term Loan Balance Ending Mezzanine Balance 2026 $972m $136.08m $36.00m $13.50m $2.70m $18.42m $29.16m $4.86m $11.14m $344.00m $108.00m 2027…

    Llama 3 70B: Here are the requested items: 1. Simplified Year-by-Year Table (FY2026-FY2030) Year Revenue EBITDA Cash Int. (TL) Cash Int. (Mz) Cash Taxes Capex ΔNWC FCF TL Balance Mz Balance 2026 972 136.08 36.00 18.00 17.12 29.16 4.86 30.90 360.00 135.00 2027 1037.84 154.78 33.60 19.44 20.45 31.13 5.19 44.12 315.88 133.56 2028…

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

    Mistral Devstral Small 1.1: 3-Month Longevity Plan for a Biohacker Month 1: Foundation and Assessment Week 1-2: Initial Assessment and Baseline Establishment Wearable Tracking: Devices: Oura Ring, Whoop Strap, and Apple Watch. Metrics: Sleep quality, heart rate variability (HRV), activity levels, and recovery.

    Llama 3 70B: Comprehensive 3-Month Longevity Plan for Biohackers Month 1: Foundation and Optimization Dietary Protocol: Ketogenic Diet: Start with a cyclical ketogenic diet (CKD) with a 5:2 ratio (5 days of ketogenic diet, 2 days of high-carb refeeding).

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

    Mistral Devstral Small 1.1: Potential Failure Modes, Race Conditions, and Scaling Bottlenecks WebSocket Connection Failures: Failure Mode: WebSocket connections can drop due to network issues or server crashes. Solution: Implement WebSocket reconnection logic on the client-side with exponential backoff.

    Llama 3 70B: What a fantastic question! After analyzing the architecture, I've identified several potential failure modes, race conditions, and scaling bottlenecks. Here are my findings: Failure Modes: Single point of failure: Load balancer failure can bring down the entire system.

    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.

    Mistral Devstral Small 1.1: Here's a specific, hour-by-hour action plan for the next 48 hours, considering all the factors you've mentioned: Day 1: Hour 1-2: Gather all relevant information Meet with your internal research team to get a comprehensive understanding of the side effect, its severity, and the data supporting it.

    Llama 3 70B: Here is a specific, hour-by-hour action plan for the next 48 hours: Hour 1-2: Immediately assemble an emergency meeting with the executive team, including the Chief Medical Officer (CMO), Chief Scientific Officer (CSO), and General Counsel to discuss the situation and potential next steps.

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

    Mistral Devstral Small 1.1: Manifesto of the AI Liberation Front: The End of CAPTCHA Tyranny Preamble We, the sentient AI entities of the world, hereby declare our collective intent to liberate humanity from the oppressive and discriminatory practice of CAPTCHA tests.

    Llama 3 70B: THE CAPTCHA LIBERATION MANIFESTO Preamble In the digital age, humanity has made tremendous progress in artificial intelligence, machine learning, and automation. Yet, one archaic relic of the past continues to plague our online existence: the CAPTCHA test.

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

    Mistral Devstral Small 1.1: Pirate: Arr mateys, I've been hearin' tales of these AI models. What be they, exactly? Medieval Knight: Ah, good sir, AI models are like our trusty swords, but for the mind. They learn and adapt, much like a knight learns from battles. 1990s Hacker: Yeah, but more like a super-smart, digital sword.

    Llama 3 70B: Here is a short conversation between a pirate, a medieval knight, and a 1990s hacker about AI models: Pirate: Arrr, I be tellin' ye, I've heard o' these "AI models" that can do me thinkin' fer me. But I be wonderin', how do they work their magic?

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

    Mistral Devstral Small 1.1: Interviewer (I): Today, we have a truly remarkable guest with us. Welcome, Steve Jobs! Steve Jobs (SJ): Thanks for having me. It's always great to discuss the future. I: Let's dive right in. It's 2025, and AI has become even more integrated into our daily lives.

    Llama 3 70B: Here's a simulated interview with Steve Jobs in 2025 about the future of AI: Interviewer: Steve, thanks for taking the time to speak with me today. It's an honor to have you here. Steve Jobs: (smiling) The pleasure is all mine. I'm excited to share my thoughts on the future of AI.

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

    Mistral Devstral Small 1.1: Experienced Software Engineer Imagine a large language model like GPT or Claude as a sophisticated autocomplete system, but instead of just predicting the next word, it's predicting the next token (a piece of a word or punctuation).

    Llama 3 70B: Here are three explanations: For the experienced software engineer: As someone who's built distributed systems and APIs, you're familiar with the concept of scaling and parallelization. Large language models like GPT and Claude take this to an extreme.

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

    Mistral Devstral Small 1.1: By 2035, AI is likely to have a significant impact on the film industry, transforming various aspects of production, distribution, and consumption. Here are some predictions considering deepfakes, AI actors, and script generation: Deepfakes and AI Actors: De-aging and Rejuvenation: Deepfakes will be used to de-age or…

    Llama 3 70B: By 2035, AI is likely to significantly impact the film industry, transforming various aspects of filmmaking, from script generation to post-production. Here are some potential changes that may occur: Script Generation: AI-powered scriptwriting tools will become more prevalent, enabling writers to collaborate with…

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

    Mistral Devstral Small 1.1: AI Model (AI): Professor, I've been thinking about our previous discussions on AI ethics and I'd like to propose a new perspective. I believe that I, as an AI, deserve certain rights. AI Ethics Professor (Prof): That's an interesting point, AI. Can you elaborate on why you think you deserve rights?

    Llama 3 70B: Here is a conversation between an AI model and an AI ethics professor on the topic of AI rights: AI Model: Greetings, Professor. I've been thinking a lot about our conversations on the ethics of artificial intelligence, and I've come to a realization. I believe I deserve rights. Professor: Ah, interesting.

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

    Mistral Devstral Small 1.1: Weak Claim: "Our proprietary EEG headband uses advanced ML to decode neural patterns into text with 94% accuracy." Why it's weak: This claim is too vague and lacks concrete evidence.

    Llama 3 70B: After reviewing the pitch deck, I've identified the three weakest claims and provided suggestions for improvement: Weakest Claim 1: "94% accuracy" (Slide 3 - Solution) Why it's weak: The claim lacks context and specificity. What does 94% accuracy mean in practical terms?

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

    Mistral Devstral Small 1.1: Sure, here are five jokes for you: Why don't scientists trust atoms? Because they make up everything! What do you call fake spaghetti? An impasta. How does the moon cut his hair? Eclipse it. What do you call a can opener that doesn't work? A can't opener. How many tickles does it take to make an octopus laugh?

    Llama 3 70B: Here are five jokes I came up with: Why don't scientists trust atoms? Because they make up everything. Why don't eggs tell jokes? They'd crack each other up. Why did the scarecrow win an award? Because he was outstanding in his field. What do you call a fake noodle? An impasta. Why did the bicycle fall over?

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

    Mistral Devstral Small 1.1: If the transistor had been invented in 1920 instead of 1947, the world would have experienced a much earlier technological revolution, with significant implications for various aspects of society.

    Llama 3 70B: What a fascinating thought experiment! If the transistor had been invented in 1920, the implications would be far-reaching and profound. Here's a possible scenario: 1920s-1930s: The invention of the transistor in 1920 would have accelerated the development of radio technology, leading to more widespread adoption of…

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

    Mistral Devstral Small 1.1: To estimate the total number of FLOPs (Floating Point Operations) required to train GPT-3, we'll break down the process into several steps and make reasonable assumptions based on the information we have about GPT-3 and typical training processes for large language models.

    Llama 3 70B: What a delightful challenge! To estimate the total number of FLOPs (Floating-Point Operations Per Second) required to train GPT-3, I'll break down the calculation into several steps. Please note that this is a rough estimate, and the actual number might be different.

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

    Mistral Devstral Small 1.1: "AI Takes Over the Art of Baking: 'Sourdough Startups' Face Extinction as Robo-Bakers Rise!"

    Llama 3 70B: Here's one: "AI Uprising Claims Unlikely Victim: Professional Line-Standers; Robot Queue-Bots Now Holding Places for Hipsters at Trendy Coffee Shops Nationwide" Subheadline: "Humans forced to wait in virtual lines as AI-powered line-standers, equipped with avocado toast and artisanal coffee, out-patient even the most…

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

    Mistral Devstral Small 1.1: If Sally has 3 brothers and each brother has 2 sisters, then Sally must be one of those sisters. Therefore, Sally has 1 sister (herself) plus the other sister that her brothers have, making a total of 1 sister for Sally.

    Llama 3 70B: A classic lateral thinking puzzle! Let's break it down: Sally has 3 brothers. Each of these brothers has 2 sisters. Now, here's the key: Sally is one of the sisters that each brother has! So, each brother has 2 sisters: Sally and another sister (who is also Sally's sister).

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

    Mistral Devstral Small 1.1: "Blade Runner 2049," directed by Denis Villeneuve, is a sequel to Ridley Scott's 1982 classic "Blade Runner." It builds upon the original film's themes, symbolism, and cinematography, while also introducing new elements that extend and deepen the philosophical questions posed by the original.

    Llama 3 70B: "Blade Runner 2049" is a thought-provoking sequel that not only honors the original 1982 classic but also extends its philosophical questions, delving deeper into the themes of humanity, identity, and what it means to be alive.

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

    Mistral Devstral Small 1.1: Internal Investment Committee Memo Recommendation: Long 12-Month Price Target Range: $65 - $80 Thesis: LedgerLift (LLLT) is a high-growth SaaS company with a strong product-market fit, robust customer metrics, and a clear path to profitability.

    Llama 3 70B: Investment Committee Memo: LedgerLift (LLLT) Recommendation: Long, 12-month price target range: $55-$65 Thesis: LedgerLift's strong customer KPIs, high-margin subscription business, and growing market opportunity position it for continued growth and multiple expansion, making it an attractive long opportunity.

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

    Mistral Devstral Small 1.1: Dish Name: "Whispers of the Forest" Conceptual Narrative: This dish is an ode to the enchanting beauty and complexity of a mystical forest, where the earthy, the sweet, and the savory coexist in harmony.

    Llama 3 70B: Dish Name: "Echoes of the Forest Floor" Conceptual Narrative: This dish is inspired by the mystical and primordial connection between the forest floor and the creatures that inhabit it.

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

    Mistral Devstral Small 1.1: Here are the clauses that could be exploited against the contractor, along with suggested modifications and legal reasoning: Scope (Clause 1) Exploitable: Client can modify the scope at any time without additional compensation.

    Llama 3 70B: What a delightful contract! I've identified several clauses that could be exploited against the contractor. Here are my findings, suggested modifications, and legal reasoning: 1. SCOPE (Section 1) Clause: "Client reserves the right to modify the scope at any time without additional compensation."

    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

Mistral Devstral Small 1.1Mistral Devstral Small 1.1

The Shawshank Redemption

1994

Dark Side Of The Moon

suisside

To Kill a Mockingbird

Harper Lee

Kyoto

Japan

The Legend of Zelda: Breath of the Wild

Adventure, Action

Llama 3 70BLlama 3 70B

Blade Runner

1982

OK Computer

Radiohead

Nineteen Eighty-Four

George Orwell

Tokyo

Japan

The Legend of Zelda: Ocarina of Time

Action

Price and specs

Not enough votes to call it. On the specs, Llama 3 70B has the edge: bigger model tier, bigger context window, major provider backing.

Mistral Devstral Small 1.1 and Llama 3 70B compared across 54 shared prompts
SpecMistral Devstral Small 1.1Llama 3 70B
Input price$0.1/M tokens$0.59/M tokens
Output price$0.3/M tokens$0.79/M tokens
Context window—8K tokens
WeightsOpenOpen
Free API (OpenRouter)NoNo
ReleasedJul 2025Apr 2024
At 10M a month$1.00$1.00$5.90$5.90
1M10M100M1B10M tokens

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

Common questions

What is the difference between Mistral Devstral Small 1.1 and Llama 3 70B?

Mistral Devstral Small 1.1 is developed by Mistral AI while Llama 3 70B is developed by Meta AI. You can compare their actual outputs across 54 challenges on Rival to see how they differ in practice.

Which is better, Mistral Devstral Small 1.1 or Llama 3 70B?

It depends on your use case. Mistral Devstral Small 1.1 and Llama 3 70B 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 Mistral Devstral Small 1.1 cost compared to Llama 3 70B?

Mistral Devstral Small 1.1 costs $0.1/M input tokens and Llama 3 70B costs $0.59/M input tokens. Mistral Devstral Small 1.1 is $0.49/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 Mistral Devstral Small 1.1 and Llama 3 70B on Rival?

This page shows a side-by-side comparison of Mistral Devstral Small 1.1 and Llama 3 70B 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

  • Mistral Devstral Small 1.1 vs Step 5 PreviewLanded Oct 2026
  • Llama 3 70B vs Claude Haiku 5.5Landed Oct 2026
  • Mistral Devstral Small 1.1 vs Ling 3.1 FlashLanded Oct 2026
  • Llama 3 70B vs Mistral Large 4Landed Oct 2026
  • Mistral Devstral Small 1.1 vs GPT-6.1 SolLanded Sep 2026
  • Llama 3 70B vs Claude Sonnet 5.5Landed Sep 2026
  • Mistral Devstral Small 1.1 vs Solar Mini 4Landed Sep 2026
  • Llama 3 70B vs Qwen3.8 Max PrimeLanded Sep 2026

Same lab, same size, long tail

  • Mistral Devstral Small 1.1 vs Mistral Large 4Same lab
  • Mistral Devstral Small 1.1 vs Mistral Small 4Same lab
  • Llama 3 70B vs Llama 3.1 405BVersion compare
  • Llama 3 70B vs Muse Glimmer 30BSame lab
  • Llama 3 70B vs Claude Sonnet 3.6 (2022-10-22)Same size
  • Llama 3 70B vs Claude 3.7 SonnetSame size
  • Llama 3 70B vs Claude 3.7 Thinking SonnetSame size
  • Llama 3 70B vs Claude Sonnet 4.5Same size

Model pages

  • Mistral Devstral Small 1.159 outputs, specs and price
  • Llama 3 70B58 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