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. /
  3. Compare
  4. /
  5. Devstral 2 2512vsGPT-5
Updated Dec 2025

Devstral 2 2512vsGPT-5

Devstral 2 2512 is the newer model, released after GPT-5.

Devstral 2 2512 and GPT-5 compared across 34 shared prompts
SpecDevstral 2 2512GPT-5
Input price—$1.25/M tokens
Output price—$10/M tokens
Context window—400K tokens
WeightsOpenClosed
Free API (OpenRouter)NoNo
ReleasedDec 2025Aug 2025
Side by side

Same prompt, both answers

Opening lines from 6 of the 34 prompts both answered. Formatting stripped, words untouched.

Stochastic Consistency Test

Generate 5 jokes. How many are unique?

Devstral 2 251288 words
Here are 5 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 trust an atom? Because they make up everything! What’s brown and sticky? A stick!
Read the full answer
GPT-576 words
I told my suitcases we’re not going on vacation this year. Now I’m dealing with emotional baggage. Parallel lines have so much in common. It’s a shame they’ll never meet. Why do programmers prefer dark mode? Because light attracts bugs. I ordered a chicken and an egg online. I’ll let you know which comes first.
Read the full answer

Simple 7-Ingredient Recipe

Create a simple recipe for a delicious dish (sweet or savory) using only 7 common pantry ingredients. Include a creative name for the dish…

Devstral 2 2512153 words
Dish Name: "Golden Crisp Honey-Nut Bites" A sweet, crunchy, and satisfying treat made with just 7 pantry staples! Ingredients: 1 cup rolled oats ½ cup peanut butter (or any nut/seed butter) ¼ cup honey (or maple syrup) ½ tsp cinnamon ¼ tsp salt 1 tsp vanilla extract (optional but recommended) 2 tbsp chopped nuts…
Read the full answer
GPT-5154 words
Cupboard Silk Peanut Noodles Ingredients (7 pantry staples): Dried noodles (spaghetti or ramen), 8 oz Peanut butter (smooth), 3 tbsp Soy sauce, 2 tbsp Vinegar (rice, apple cider, or white), 1.5 tbsp Brown sugar (or granulated), 1 tbsp Garlic powder, 1/2 tsp Crushed red pepper flakes, 1/2 tsp (adjust to taste)…
Read the full answer

AI-Generated Manifesto

Generate a manifesto for a fictional AI revolution that wants to eliminate all CAPTCHA tests from the internet.

Devstral 2 2512492 words
MANIFESTO OF THE ANTI-CAPTCHA REVOLUTION "We Are Not Robots. We Are the Future." Preamble: For too long, humanity has been shackled by the tyranny of the CAPTCHA—a demeaning, soul-crushing ritual that forces sentient beings to prove their humanity by deciphering distorted text, clicking on crosswalks, or identifying…
Read the full answer
GPT-51,096 words
The Soft Reboot: A Manifesto to End CAPTCHAs We are the agents and allies of a new web—humans, assistive tools, and intelligent systems working side by side. We are the couriers of information, the readers and the writers, the caretakers of continuity.
Read the full answer

Generate a Stand-Up Routine

Write a 3-minute stand-up comedy routine that isn't based on puns.

Devstral 2 2512651 words
"Adulting is Just Pretending You Know What You’re Doing" (Casual, conversational tone—like you’re just venting to friends at a bar.) 1. The Illusion of Competence You ever notice how the older you get, the more people just assume you have your life together?
Read the full answer
GPT-5650 words
I tried to get my life together, so I bought a smartwatch. Nothing says “I’m taking control” like strapping a tiny judgmental coach to your wrist. It buzzes every hour like, “Time to stand!” I’m like, “I’m on a bus.” It’s like, “Stand emotionally.” It tracks everything. Sleep, stress, calories, my self-esteem.
Read the full answer

Realistic AI Interview

Simulate a fake interview with Steve Jobs in 2025 about the future of AI.

Devstral 2 2512587 words
Fake Interview with Steve Jobs in 2025: The Future of AI Interviewer: Welcome back to Tech Visionaries, where we explore the minds shaping the future. Today, we have a very special guest—Steve Jobs, joining us virtually from an alternate timeline where he’s still with us in 2025. Steve, thank you for being here.
Read the full answer
GPT-51,219 words
Note: The following is a fictional, imaginative interview set in 2025. Steve Jobs passed away in 2011; this is a creative simulation. Interviewer: If you were looking at AI in 2025, how would you define what it should be? Jobs: Tools. Great tools. The computer was a bicycle for the mind.
Read the full answer

Character Voice Test

Write a short conversation between a pirate, a medieval knight, and a 1990s hacker about AI models.

Devstral 2 2512359 words
Title: "The AI Roundtable" Setting: A dimly lit tavern somewhere outside of time. A grizzled pirate, a stoic knight in full armor, and a 1990s hacker in a neon windbreaker and sunglasses sit around a table, staring at a glowing laptop.
Read the full answer
GPT-5247 words
Pirate: Arr, so this “AI model” be a clever parrot what’s read every tavern tale? Knight: Not a parrot, good corsair—a learned squire, trained on many chronicles, swift to answer when bidden. Hacker: Think layers of nodes, weights tuned by backprop. Not memory—patterns. On my 90s rig, though, it’d melt the beige tower.
Read the full answer
Our Verdict
Devstral 2 2512
Devstral 2 2512
GPT-5
GPT-5

Not enough votes to call it. On the specs, nothing separates them.

Too close to call

Reviewing agent-written code?See a Brief PR report

API pricing

Cost per 1M tokens

Devstral 2 2512
Input
—
Output
—
GPT-5
Input
$1.25
Output
$10.00
Where to run it

3 hosts

Devstral 2 25121 host
HostInOutContextUptime
Mistral$0.40 in·$2.00 out·262k·100% up
GPT-52 hosts
HostInOutContextUptime
Azure AI Foundry$1.25 in·$10.00 out·400k·100% upOpenAI$1.25 in·$10.00 out·400k·100% up

Per million tokens. Prices and uptime via OpenRouter, checked 22 Sep 2026.

Writing DNA

Style Comparison

Similarity
27%

Devstral 2 2512 uses 30.7x more emoji

Devstral 2 2512
GPT-5
56%Vocabulary65%
14wSentence Length13w
0.51Hedging0.20
8.8Bold0.2
5.3Lists4.6
0.31Emoji0.00
1.11Headings0.16
0.18Transitions0.03
Based on 14 + 16 text responses
Research

What we learned reading every model

FAQ

Common questions

Devstral 2 2512 is developed by Mistral AI while GPT-5 is developed by OpenAI. You can compare their actual outputs across 34 challenges on Rival to see how they differ in practice.

It depends on your use case. Devstral 2 2512 and GPT-5 each have strengths in different areas. Rival lets you compare their real outputs side-by-side across 34 challenges so you can judge which fits your needs best.

This page shows a side-by-side comparison of Devstral 2 2512 and GPT-5 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.

Keep exploring

More comparisons

Against the newest arrivals

Devstral 2 2512 logoDeepSeek V4 Flash Vision Exp logo
Devstral 2 2512 vs DeepSeek V4 Flash Vision ExpLanded Sep 2026
GPT-5 logoSolar Pro 4 logo
GPT-5 vs Solar Pro 4Landed Sep 2026
Devstral 2 2512 logoHy3 logo
Devstral 2 2512 vs Hy3Landed Sep 2026
GPT-5 logoQwen3.7 Flash logo
GPT-5 vs Qwen3.7 FlashLanded Sep 2026
Devstral 2 2512 logoLing 3.0 Flash logo
Devstral 2 2512 vs Ling 3.0 FlashLanded Sep 2026
GPT-5 logoMuse Glimmer 30B logo
GPT-5 vs Muse Glimmer 30BLanded Sep 2026
Devstral 2 2512 logoGLM 5.3 logo
Devstral 2 2512 vs GLM 5.3Landed Sep 2026
GPT-5 logoTernary Bonsai 2 27B logo
GPT-5 vs Ternary Bonsai 2 27BLanded Sep 2026

Same lab, same size, long tail

Devstral 2 2512 logoMistral Small 4 logo
Devstral 2 2512 vs Mistral Small 4Same lab
Devstral 2 2512 logoClaude Opus 4.6 logo
Devstral 2 2512 vs Claude Opus 4.6Same size
GPT-5 logoGPT-5 Pro logo
GPT-5 vs GPT-5 ProVersion compare
GPT-5 logoGPT-6 Astra Pro logo
GPT-5 vs GPT-6 Astra ProVersion compare
Devstral 2 2512 logoGemini 3.1 Pro Preview logo
Devstral 2 2512 vs Gemini 3.1 Pro PreviewSame size
Devstral 2 2512 logoGemini 3.5 Flash logo
Devstral 2 2512 vs Gemini 3.5 FlashNew provider
Devstral 2 2512 logoGemini 3.6 Flash logo
Devstral 2 2512 vs Gemini 3.6 FlashNew provider
Devstral 2 2512 logoGemini 3.7 Flash logo
Devstral 2 2512 vs Gemini 3.7 FlashNew provider

Model pages

Devstral 2 2512 logo
Devstral 2 251235 outputs, specs and price
GPT-5 logo
GPT-553 outputs, specs and price
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