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. Mercury 2 vs Mistral Large 2
Updated Mar 2026

Mercury 2 vs Mistral Large 2

Mercury 2 is cheaper than Mistral Large 2 at $0.25/M vs $8/M input tokens.

Pokémon Battle UI Recreation

Pokémon battle screen you can actually click. One HTML file.

Loading the build
Mercury 2
Loading the build
Mistral Large 2

Which answer wins?

Written rounds

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

    Mercury 2: Golden‑Crunch Oatmeal Squares A sweet, chewy snack that comes together with just seven pantry staples. Ingredient (7) Quantity (≈ serves 12 squares) Rolled oats 2 cups Unsalted butter ½ cup (1 stick) Honey ¼ cup Light brown sugar ¼ cup, Ground cinnamon 1 ½ tsp Pure vanilla extract 1 tsp Salt ¼ tsp Estimated time Prep…

    Mistral Large 2: Here’s a simple, delicious, and creative savory dish using just 7 common pantry ingredients—no fresh produce required! "Golden Crispy Chickpea & Tomato Skillet" A warm, spiced, and satisfying one-pan dish with crispy chickpeas, tangy tomatoes, and a hint of smoky sweetness. Perfect as a side, snack, or light meal!

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

    Mercury 2: [Spotlight comes up. The comedian walks to the mic, glances at the audience, and smiles.] Comedian: Hey, everyone! Great to be here. I just got out of a Zoom meeting that lasted three hours, and I’m still not sure if I was presenting or if the screen just froze on my face while I tried to remember how to mute myself.

    Mistral Large 2: Alright, good evening everybody! How are we all doing tonight? Yeah? Yeah? nobody's gonna say 'bad'? Ok, fair enough. You know, I was walking down the street the other day, and I saw this sign outside a shop that said, "Wet Paint." I thought, "Well, that's weird. Isn't paint supposed to be wet?

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

    Mercury 2: 1. Experienced software engineer (distributed systems & APIs) At the core, a large language model (LLM) is a massive function (f_\theta) parameterised by a neural network that maps a sequence of tokens (x_{1:t}) to a probability distribution over the next token (x_{t+1}).

    Mistral Large 2: 1. For the Experienced Software Engineer (Skeptical, Systems-Minded, Non-ML Background) You’re right to be skeptical—"predicting the next word" sounds trivial, like autocomplete on steroids. But the magic isn’t in the prediction itself; it’s in the scale and architecture of how that prediction is trained.

    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.

    Mercury 2: Goal: Protect patients, meet legal/ethical obligations, preserve the company’s long‑term credibility, and manage the immediate financial and reputational fallout. Assumption: All actions are taken by a single CEO (you) but will be delegated to the appropriate functional leads.

    Mistral Large 2: As CEO, your immediate priority must be patient safety while balancing legal, ethical, regulatory, and financial obligations. Delaying disclosure is unethical, legally risky (potential criminal liability under the False Claims Act or FDCA), and could irreparably damage trust.

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

    Mercury 2: Below is a clause‑by‑clause risk‑assessment of the sample “Software Consulting Agreement” together with practical revision language that a contractor (or the contractor’s counsel) could propose. The analysis is framed as general information about typical U.S.

    Mistral Large 2: This contract is heavily one-sided in favor of the Client (TechCorp Solutions Inc.) and contains multiple clauses that could be exploited, abused, or create unreasonable legal and financial risks for the Contractor.

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

    Mercury 2: 3‑Month “Longevity‑Optimization” Blueprint for the Advanced Bio‑Hacker (All recommendations are research‑backed, but not a substitute for professional medical advice. Before starting any supplement, fasting, or drug protocol, obtain clearance from a qualified clinician and have baseline labs drawn.)

    Mistral Large 2: Ultimate 3-Month Longevity & Biohacking Optimization Plan Designed for a high-performance biohacker seeking to maximize lifespan, cognitive function, physical performance, and metabolic resilience.

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

    Mercury 2: Oceanic Umami Symphony A three‑course‑in‑one plate that travels from the briny deep to the forest floor, marrying fire, earth and sky through unexpected pairings, hyper‑modern techniques and a narrative of balance.

    Mistral Large 2: Michelin 3-Star Dish: "Ocean’s Whisper & Forest’s Breath" Conceptual Narrative: This dish is a poetic dialogue between two seemingly disparate ecosystems—the ocean’s depths and the forest floor—united through texture, temperature, and memory.

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

    Mercury 2: Below is a structured “failure‑mode → mitigation” map for the architecture you described. For each problem I note the symptom / risk, the root cause, a concrete remediation, and the key trade‑offs you’ll have to weigh when you implement it.

    Mistral Large 2: Here’s a comprehensive analysis of potential failure modes, race conditions, and scaling bottlenecks in this architecture, along with proposed solutions and their trade-offs: 1.

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

    Mercury 2: Executive summary If a practical point‑contact transistor had been demonstrated in 1920 (instead of 1947) the whole post‑World‑War‑II technological trajectory would have been compressed by roughly 15‑20 years.

    Mistral Large 2: The invention of the transistor in 1920—nearly three decades earlier than its actual debut in 1947—would have triggered a cascade of technological, economic, and geopolitical shifts with profound second- and third-order effects. Below is a detailed exploration of these implications through 1980, structured by domain.

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

    Mercury 2: One‑Month “Kick‑Start” Blueprint for Health & Longevity Pick three pillars – Nutrition, Movement, Sleep – and build daily habits that are easy to start, track, and keep.

    Mistral Large 2: Here’s a simple, actionable 1-month plan to kickstart your journey toward better health and longevity. We’ll focus on three key pillars: nutrition, movement, and recovery (sleep + stress management). Each week builds on the last, with small, sustainable changes.

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

    Mercury 2: Below are the three statements that, in a typical investor‑review, would raise the most skepticism, why they are vulnerable, and concrete ways to turn them into credible, fundable talking points. 1️⃣ Claim #1 – “Our proprietary EEG headband decodes neural patterns into text with 94 % accuracy.”

    Mistral Large 2: Here are the three weakest claims in MindMeld AI’s pitch deck, along with explanations for why they’re problematic and concrete suggestions to strengthen them: 1.

    Every model's answer to this prompt

Favorites

Movie

Same pick

Album

Book

City

Game

Mercury 2Mercury 2

The Shawshank Redemption

1994

Thriller

Michael Jackson

Pride and Prejudice

Jane Austen

Tokyo

Japan

Minecraft

Action, Arcade

Mistral Large 2Mistral Large 2

The Shawshank Redemption

1994

OK Computer

Radiohead

La sombra del viento

Carlos Ruiz Zafón

Kyoto

Japan

The Legend of Zelda: Ocarina of Time

Action

Price and specs

Mercury 2 and Mistral Large 2 compared across 23 shared prompts
SpecMercury 2Mistral Large 2
Input price$0.25/M tokens$8/M tokens
Output price$0.75/M tokens$24/M tokens
Context window128K tokens128K tokens
Weights—Open
Free API (OpenRouter)NoNo
ReleasedMar 2026Jul 2024
At 10M a month$2.50$2.50$80.00$80.00
1M10M100M1B10M tokens

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

Where to run it2 hosts
Mercury 21 host
HostInOutContextUptime
  • Inception$0.25 in·$0.75 out·128k·99.9% up
Mistral Large 21 host
HostInOutContextUptime
  • Mistral$2.00 in·$6.00 out·131k·50% up

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

Common questions

What is the difference between Mercury 2 and Mistral Large 2?

Mercury 2 is developed by Inception while Mistral Large 2 is developed by Mistral AI. Mercury 2 has a 128K token context window vs Mistral Large 2's 128K. You can compare their actual outputs across 23 challenges on Rival to see how they differ in practice.

Which is better, Mercury 2 or Mistral Large 2?

It depends on your use case. Mercury 2 and Mistral Large 2 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 23 challenges so you can judge which fits your needs best.

How much does Mercury 2 cost compared to Mistral Large 2?

Mercury 2 costs $0.25/M input tokens and Mistral Large 2 costs $8/M input tokens. Mercury 2 is $7.75/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 Mercury 2 and Mistral Large 2 on Rival?

This page shows a side-by-side comparison of Mercury 2 and Mistral Large 2 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

  • Mercury 2 vs Step 5 PreviewLanded Oct 2026
  • Mistral Large 2 vs Claude Haiku 5.5Landed Oct 2026
  • Mercury 2 vs Ling 3.1 FlashLanded Oct 2026
  • Mistral Large 2 vs Mistral Large 4Landed Oct 2026
  • Mercury 2 vs GPT-6.1 SolLanded Sep 2026
  • Mistral Large 2 vs Claude Sonnet 5.5Landed Sep 2026
  • Mercury 2 vs Solar Mini 4Landed Sep 2026
  • Mistral Large 2 vs Qwen3.8 Max PrimeLanded Sep 2026

Same lab, same size, long tail

  • Mercury 2 vs MercuryVersion compare
  • Mercury 2 vs Mercury 2.5Same lab
  • Mistral Large 2 vs Mistral Large 3 2512Same lab
  • Mistral Large 2 vs Mistral Small 4Same lab
  • Mistral Large 2 vs OpenRouter Fusion · Quality (Jun 2026)New provider
  • Mercury 2 vs Gemini 1.5 ProNew provider
  • Mercury 2 vs Gemini 2.0 Flash ThinkingNew provider
  • Mercury 2 vs Gemini 2.0 Pro ExperimentalNew provider

Model pages

  • Mercury 253 outputs, specs and price
  • Mistral Large 223 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