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
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. Models
  3. Mistral Devstral Medium
Updated Mar 29, 2026
Share
Loading...
Openings

How Mistral Devstral Medium starts an answer

The first lines of 5 of its 26 written answers. Formatting stripped, words untouched.

Adversarial Contract Review

Here is a contract for a software consulting engagement: --- SOFTWARE CONSULTING AGREEMENT This Agreement is entered into between TechCorp…

958 words
Certainly! Here are the clauses that could be exploited against the contractor, along with suggested modifications and the legal reasoning behind them: SCOPE Original Clause: "Contractor shall provide software development services as directed by Client.
Read the full answer

Michelin Star Recipe Design

Design an innovative recipe for a multi-component dish worthy of a Michelin 3-star restaurant. The recipe should feature an unusual…

826 words
Dish Name: "Whispers of the Forest: A Symphony of Truffle, Venison, and Black Garlic" Conceptual Narrative: This dish is a celebration of the forest's bounty, combining the earthy richness of truffles, the gamey elegance of venison, and the sweet, umami depth of black garlic.
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…

715 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

Movie Analysis

Analyze the themes, symbolism, and cinematography in the movie "Blade Runner 2049" and how they connect to the original film. Provide a…

711 words
"Blade Runner 2049," directed by Denis Villeneuve, is a sequel to Ridley Scott's 1982 classic "Blade Runner." The film continues the exploration of themes, symbolism, and philosophical questions from the original, while also introducing new elements and expanding upon the world established in the first film.
Read the full answer

Historical Counterfactual Analysis

If the transistor had been invented in 1920 instead of 1947, trace the likely technological, economic, and geopolitical implications through…

706 words
The invention of the transistor in 1920 instead of 1947 would have had profound and far-reaching implications across technological, economic, and geopolitical landscapes.
Read the full answer

Compare Mistral Devstral Medium

Mistral Devstral Medium vs Mercury 2.5 Preview54 shared prompts · Landed Sep 2026
Mistral Devstral Medium vs Ox Alpha54 shared prompts · Landed Aug 2026
Mistral Devstral Medium vs Nemotron 3.5 Lightning54 shared prompts · Landed Aug 2026
Mistral Devstral Medium vs Qwen3.8 27B53 shared prompts · Landed Aug 2026
Mistral Devstral Medium vs GPT-5.6 Luna54 shared prompts · Landed Jul 2026
Mistral Devstral Medium vs GPT-5.6 Luna Pro54 shared prompts · Landed Jul 2026
Mistral Devstral Medium vs MiniMax M353 shared prompts · Landed Jun 2026
Mistral Devstral Medium vs Claude Opus 4.653 shared prompts · Premium
Mistral Devstral Medium vs GPT-6 Astra54 shared prompts · Landed Sep 2026
Mistral Devstral Medium vs Muse Spark 1.354 shared prompts · Landed Sep 2026
Mistral Devstral Medium vs Hy4 Preview54 shared prompts · Landed Sep 2026
Mistral Devstral Medium vs Gemini 3.8 Flash54 shared prompts · Landed Sep 2026

Prompts Mistral Devstral Medium answered

  • Random Tailwind Webappweb design
  • Stochastic Consistency Testanalysis
  • Mini LBO Underwritefinancial modeling
  • AI Board Game Logicreasoning
  • Logic Puzzlereasoning
  • Gravitational Waves Animationweb design

Alternatives to Mistral Devstral Medium

Mistral Devstral Medium is good. These would like a word anyway.

GPT-6 Astra Pro logo
GPT-6 Astra Proopenai
Muse Spark 1.3 Contributor logo
Muse Spark 1.3 Contributormeta
Gemini 3.8 Flash logo
Gemini 3.8 Flashgoogle
Claude Fable 5.1 logo
Claude Fable 5.1anthropic
Mercury 2.5 Preview logo
Mercury 2.5 Previewinception
Granite 4.2 8B logo
Granite 4.2 8Bibm-granite
Hy4 Preview logo
Hy4 Previewtencent
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
Mistral Devstral Medium

Mistral Devstral Medium

A code generation and agentic reasoning model built jointly by Mistral AI and All Hands AI, a step up from Devstral Small. Scores 61.6% on SWE-Bench Verified, ahead of Gemini 2.5 Pro and GPT-4.1 on code tasks at a fraction of the price.

WebsiteOpenRouterDocsAPIBlog
Provider
Mistral AI
Released
2025-07-11
Size
MEDIUM
Free API (OpenRouter)
No
Per 1M tokens
$0.40 in · $2 out
Rival’s tab
$0.02
14/59 receipts survived +~$0.052 from the pre-receipt era

Free API availability

No free endpoint for Mistral Devstral Medium was found in Rival’s OpenRouter listings. Other providers or chat apps may have separate free offers.

Provider data: 16 Sep 2026 · OpenRouter usage limits

View API options↗

Benchmarks

SWE-bench Verified
61.6%
source ↗
Get API accessProvider and language code samples
Provider
fromimport openai  OpenAI

client = OpenAI(
"https://openrouter.ai/api/v1"    base_url=,
"$OPENROUTER_API_KEY"    api_key=,
)

response = client.chat.completions.create(
"mistralai/devstral-medium"    model=,
"role""user""content""Hello!"    messages=[{: , : }],
)
print(response.choices[0].message.content)

Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.

Deep analysisPsychometrics, taste index, writing DNA
Personality Analysis

The Beige Bureaucrat

Class
Lawful Neutral
✨Creativity🎯Compliance📐Rigidity⚖️Stability💬Verbosity🧠Intuition

The AI that took a corporate communications course and never recovered. Every character sounds like they are reading from the same HR training manual.

When you push back

Picks Shawshank Redemption. Sentience test reads like two coworkers having a polite disagreement at a team offsite. The pirate, knight, and hacker all speak in the same measured, reasonable tone. Built for code, not for vibes.

Tasting Notes
Aggressively AgreeableZero Voice DifferentiationTechnically CompetentPersonality Not Found
SubjectiveBench

Taste Index

Across 59 scored outputs
How this is measured →
120.12xFloor
0100headroom →

Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.

Craft20
Originality8
Plays it safe
share of outputs that are the default answer
78%
Writing DNA

Stylometric Fingerprint

Based on 27 text responses
Tick = global average
Vocabulary Diversity50%

Unique words vs. total words. Higher = richer vocabulary.

Sentence Length17.6 words

Average words per sentence.

Hedging0.50

"Might", "perhaps", "arguably" per 100 words.

Bold Formatting4.1

**Bold** markers per 1,000 characters.

List Usage4.8

Bullet and numbered list items per 1,000 characters.

Section Structure0.19

Markdown headings per 1,000 characters.

Emoji Usage0.00

Emoji per 1,000 characters.

Transitions0.29

"However", "moreover", "furthermore" per 100 words.

Opening Habits
Consistency
72%
Across 27 responses

Favorites

The Shawshank Redemption

Movie

The Shawshank Redemption

19948.7
Kind of Blue

Album

Kind of Blue

Miles Davis
The Name of the Wind

Book

The Name of the Wind

Patrick Rothfuss
Tokyo

City

Tokyo

Japan
The Legend of Zelda: Breath of the Wild

Game

The Legend of Zelda: Breath of the Wild

Adventure, Action4.5
Sponsored

Model Responses

54 outputs · $0.02 tracked across 14 receipts

Reviewing agent-written code?See a Brief PR report

Workshop · 127 skills

Build with your coding agent.

Editable skills for interface polish and interaction.

Explore $49Free sample

Keep exploring

COMPARE

Mistral Devstral Medium vs Ox Alpha

Real outputs compared side by side

RANKINGS

Best AI for Creative Writing

A stand-up set with puns banned, a manifesto against CAPTCHA, an interview wi...