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. GPT-5 Codex vs Mistral Large 2
Updated Sep 2025

GPT-5 Codex vs Mistral Large 2

GPT-5 Codex is the newer model, released after Mistral Large 2.

Pokémon Battle UI Recreation

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

Loading the build
GPT-5 Codex
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.

    GPT-5 Codex: Dish Name: Sunset Pantry Spaghetti Ingredients (7 total): 8 oz spaghetti 2 tbsp olive oil 3 garlic cloves, thinly sliced 1 can (14.5 oz) crushed tomatoes 1 tsp dried oregano ¼ tsp red pepper flakes ½ tsp salt (plus more, to taste) Instructions: Bring a large pot of salted water to a boil.

    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.

    GPT-5 Codex: Hey everybody, how you doing? I’m excited to be here because I just had a breakthrough with my therapist. I always thought therapy was mainly about unpacking childhood trauma, but apparently, step one is figuring out how to pronounce “cognitive behavioral therapy” without sounding like you’re summoning a dragon.

    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 month, three habits, someone starting from nothing.

    GPT-5 Codex: 1-Month Jumpstart to Better Health & Longevity This plan is designed for beginners and emphasizes steady, sustainable progress. It focuses on three key areas: diet, movement, and sleep & stress. Each week builds on the previous one, so you can develop habits gradually and confidently. 🥗 1.

    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
  • Three-month biohacker protocol, with dosages and biomarkers named.

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

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

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

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

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

    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.

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

    Every model's answer to this prompt

Favorites

Movie

Album

Book

City

Game

GPT-5 CodexGPT-5 Codex
No pick

Blade Runner

1982

Kind of Blue

Miles Davis

No pick

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

Not enough votes to call it. On the specs, GPT-5 Codex has the edge: bigger model tier, newer, major provider backing.

GPT-5 Codex and Mistral Large 2 compared across 22 shared prompts
SpecGPT-5 CodexMistral Large 2
Input price—$8/M tokens
Output price—$24/M tokens
Context window—128K tokens
Weights—Open
Free API (OpenRouter)NoNo
ReleasedSep 2025Jul 2024
At 10M a month–not listed$80.00$80.00
1M10M100M1B10M tokens

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

Where to run it1 host
GPT-5 Codex

No hosts listed on OpenRouter.

Mistral Large 21 host
HostInOutContextUptime
  • Mistral$2.00 in·$6.00 out·131k·100% up

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

Common questions

What is the difference between GPT-5 Codex and Mistral Large 2?

GPT-5 Codex is developed by OpenAI while Mistral Large 2 is developed by Mistral AI. You can compare their actual outputs across 22 challenges on Rival to see how they differ in practice.

Which is better, GPT-5 Codex or Mistral Large 2?

It depends on your use case. GPT-5 Codex and Mistral Large 2 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 22 challenges so you can judge which fits your needs best.

How can I compare GPT-5 Codex and Mistral Large 2 on Rival?

This page shows a side-by-side comparison of GPT-5 Codex 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

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

Same lab, same size, long tail

  • GPT-5 Codex vs GPT-6 Luna ProSame lab
  • GPT-5 Codex vs GPT-6 Sol ProSame lab
  • Mistral Large 2 vs Mistral Large 3 2512Same lab
  • Mistral Large 2 vs Mistral Small 4Same lab
  • Mistral Large 2 vs GPT-5.1Cross-provider
  • GPT-5 Codex vs GPT-5.1-Codex-MiniSame lab
  • Mistral Large 2 vs GPT-5.2Cross-provider
  • Mistral Large 2 vs GPT-5.3 ChatSame size

Model pages

  • GPT-5 Codex50 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