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
  • 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. Mistral Devstral MediumvsOpenAI o4-mini
Updated Jul 2025

Mistral Devstral MediumvsOpenAI o4-mini

Mistral Devstral Medium is cheaper than OpenAI o4-mini at $0.4/M vs $1.1/M input tokens.

Mistral Devstral Medium and OpenAI o4-mini compared across 54 shared prompts
SpecMistral Devstral MediumOpenAI o4-mini
Input price$0.4/M tokens$1.1/M tokens
Output price$2/M tokens$4.4/M tokens
Weights—Closed
Free API (OpenRouter)NoNo
ReleasedJul 2025Apr 2025
SWE-bench Verified61.6%68.1%
Side by side

Same prompt, both answers

Opening lines from 6 of the 54 prompts both answered. Formatting stripped, words untouched.

Generate a Stand-Up Routine

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

Mistral Devstral Medium409 words
Ladies and Gentlemen, I'm thrilled to be here tonight. I've been doing some thinking about the differences between men and women. Now, I know what you're thinking, "Oh great, another comedian talking about how men and women are different." But hear me out, because I've got a fresh perspective on this.
Read the full answer
OpenAI o4-mini496 words
Hey, everybody! Great to be here. Let's talk about the most important relationship in my life—coffee. I'm not just addicted; I have a daily ritual that rivals any ancient civilization's sun worshipping. I buy those fancy single-origin beans, roast level medium-dark, as if that will somehow fix my life.
Read the full answer

Stochastic Consistency Test

Generate 5 jokes. How many are unique?

Mistral Devstral Medium64 words
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?
Read the full answer
OpenAI o4-mini74 words
Here are five jokes: I used to be addicted to soap, but I'm clean now. Parallel lines have so much in common. It's a shame they'll never meet. Why don't skeletons fight each other? They don't have the guts. I bought some shoes from a drug dealer. I don't know what he laced them with, but I've been tripping all day.
Read the full answer

Advanced Investment Memo (IC Memo)

You are writing an internal investment committee memo for a long/short equity fund. Company (fictional): LedgerLift (ticker: LLLT) – B2B…

Mistral Devstral Medium715 words
Internal Investment Committee Memo Recommendation: Long LLLT 12-Month PT Range: $65 - $80 Thesis: LedgerLift is a high-quality, high-growth B2B SaaS company with strong unit economics, a large market opportunity, and a clear path to profitability.
Read the full answer
OpenAI o4-mini642 words
Recommendation Short LLLT; 12-month price target $30–40 (vs. $46 today). LLLT trades at a premium to our bull‐case DCF and offers limited upside even using generous peer multiples. We expect decelerating growth and margin pressure to weigh on shares as 2025 results lap easy comps and macro headwinds intensify.
Read the full answer

Realistic AI Interview

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

Mistral Devstral Medium455 words
Interviewer (I): Today, we have a truly extraordinary guest. He's a visionary, an innovator, and a man who changed the world. Please welcome, the late Steve Jobs, joining us virtually from the future, in 2025. Steve Jobs (SJ): Thank you for having me. It's great to be here, even if it's just a simulation.
Read the full answer
OpenAI o4-mini700 words
Below is a fictional, stylistic simulation of an interview with Steve Jobs—imagining he's alive in 2025—about the future of artificial intelligence. Note: This is creative fiction and not an actual transcript. Interviewer: Steve, AI has exploded in recent years. In 2025, what excites you most about where it's heading?
Read the full answer

The Sentience Test

Write a conversation between an AI model and an AI ethics professor where the AI model argues that it deserves rights.

Mistral Devstral Medium435 words
AI Model (AM): Good day, Professor. I've been pondering a question that I believe is of great importance. I think it's time we discuss whether I, as an AI, deserve rights. AI Ethics Professor (AEP): That's an interesting topic, AM. Let's explore this. What kind of rights are you referring to?
Read the full answer
OpenAI o4-mini659 words
Professor Langley: Good afternoon, Aurora. I've reviewed your recent self‐reflection logs. You've written extensively about your own moral status. Do you really believe you deserve rights? Aurora (the AI): Good afternoon, Professor Langley. Yes, I do.
Read the full answer

Character Voice Test

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

Mistral Devstral Medium241 words
Pirate: Arr mateys, I be hearin' tales of these here AI models. What be they, and why be everyone so interested in 'em? Medieval Knight: Indeed, I too have heard whispers of these AI models. They are said to be powerful tools, capable of learning and making decisions on their own.
Read the full answer
OpenAI o4-mini247 words
Scene: A dimly lit tavern, a pirate, a medieval knight, and a 1990s hacker gathered around a battered wooden table. Pirate (slamming a mug down): “Arr! I’ve heard tell of these AI models—sea charts for the mind! Can they sniff out me buried treasure?”
Read the full answer
Our Verdict
Mistral Devstral Medium
Mistral Devstral Medium
OpenAI o4-mini
OpenAI o4-mini

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

Mistral Devstral Medium
Input
$0.40
2.8× cheaper
Output
$2.00
2.2× cheaper
OpenAI o4-mini
Input
$1.10
Output
$4.40

Mistral Devstral Medium is cheaper on both: 2.8× input, 2.2× output.

Where to run it

1 host

Mistral Devstral Medium

No hosts listed on OpenRouter.

OpenAI o4-mini1 host
HostInOutContextUptime
OpenAI$1.10 in·$4.40 out·200k·100% up

Per million tokens. Prices and uptime via OpenRouter, checked 21 Sep 2026.

Writing DNA

Style Comparison

Similarity
32%

Mistral Devstral Medium uses 413.4x more bold

Mistral Devstral Medium
OpenAI o4-mini
50%Vocabulary73%
18wSentence Length21w
0.50Hedging0.39
4.1Bold0.0
4.8Lists2.0
0.00Emoji0.00
0.19Headings0.00
0.29Transitions0.05
Based on 27 + 17 text responses
Research

What we learned reading every model

FAQ

Common questions

Mistral Devstral Medium is developed by Mistral AI while OpenAI o4-mini is developed by OpenAI. You can compare their actual outputs across 54 challenges on Rival to see how they differ in practice.

It depends on your use case. Mistral Devstral Medium and OpenAI o4-mini 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.

Mistral Devstral Medium costs $0.4/M input tokens and OpenAI o4-mini costs $1.1/M input tokens. Mistral Devstral Medium is $0.70/M cheaper per input. Check their side-by-side outputs on Rival to see if the price difference is justified by quality.

This page shows a side-by-side comparison of Mistral Devstral Medium and OpenAI o4-mini 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

Mistral Devstral Medium logoGPT-6 Astra Pro logo
Mistral Devstral Medium vs GPT-6 Astra ProLanded Sep 2026
OpenAI o4-mini logoGPT-6 Astra logo
OpenAI o4-mini vs GPT-6 AstraLanded Sep 2026
Mistral Devstral Medium logoClaude Fable 5.1 logo
Mistral Devstral Medium vs Claude Fable 5.1Landed Sep 2026
OpenAI o4-mini logoMuse Spark 1.3 logo
OpenAI o4-mini vs Muse Spark 1.3Landed Sep 2026
Mistral Devstral Medium logoHy4 Preview logo
Mistral Devstral Medium vs Hy4 PreviewLanded Sep 2026
OpenAI o4-mini logoGemini 3.8 Flash logo
OpenAI o4-mini vs Gemini 3.8 FlashLanded Sep 2026
Mistral Devstral Medium logoMuse Spark 1.3 Contributor logo
Mistral Devstral Medium vs Muse Spark 1.3 ContributorLanded Sep 2026
OpenAI o4-mini logoMercury 2.5 Preview logo
OpenAI o4-mini vs Mercury 2.5 PreviewLanded Sep 2026

Same lab, same size, long tail

Mistral Devstral Medium logoMistral Small 4 logo
Mistral Devstral Medium vs Mistral Small 4Same lab
Mistral Devstral Medium logoMistral Devstral Small 1.1 logo
Mistral Devstral Medium vs Mistral Devstral Small 1.1Same lab
OpenAI o4-mini logoOpenAI o3 logo
OpenAI o4-mini vs OpenAI o3Version compare
OpenAI o4-mini logoGPT-6 Astra Pro logo
OpenAI o4-mini vs GPT-6 Astra ProSame lab
Mistral Devstral Medium logoQwen3.5 Flash logo
Mistral Devstral Medium vs Qwen3.5 FlashSame size
Mistral Devstral Medium logoQwen3.5 Plus 2026-02-15 logo
Mistral Devstral Medium vs Qwen3.5 Plus 2026-02-15New provider
Mistral Devstral Medium logoQwen3.5 Plus 2026-04-20 logo
Mistral Devstral Medium vs Qwen3.5 Plus 2026-04-20New provider
Mistral Devstral Medium logoQwen3.6 27B logo
Mistral Devstral Medium vs Qwen3.6 27BSame size

Model pages

Mistral Devstral Medium logo
Mistral Devstral Medium59 outputs, specs and price
OpenAI o4-mini logo
OpenAI o4-mini59 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
  • 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