Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Mistral Devstral Small 1.1 vs GPT-5
Compare Mistral Devstral Small 1.1 by Mistral AI against GPT-5 by OpenAI, tested across 47 shared challenges. Updated April 2026.
Which is better, Mistral Devstral Small 1.1 or GPT-5?
Mistral Devstral Small 1.1 and GPT-5 are both competitive models. Mistral Devstral Small 1.1 costs $0.1/M input tokens vs $1.25/M for GPT-5. Compare their real outputs side by side below.
Key Differences Between Mistral Devstral Small 1.1 and GPT-5
Mistral Devstral Small 1.1 is made by mistral while GPT-5 is from openai. On pricing, Mistral Devstral Small 1.1 costs $0.1/M input tokens vs $1.25/M for GPT-5.
Loading share button...
Mistral Devstral Small 1.1vsGPT-5
47 fights queued
Why Mistral Devstral Small 1.1?
29.5x cheaper overall$0.10/M in · $0.30/M out
Why GPT-5?
Leads 1 of 1 benchmarks
Stronger on SWE-bench Verified74.9% vs 46.8%
Mistral Devstral Small 1.1GPT-5
Input price
$0.10/M
$1.25/M
Output price
$0.30/M
$10.00/M
Context
—
400K
Released
Jul 2025
Aug 2025
Benchmarks1 common
Favorites
Mistral Devstral Small 1.1GPT-5
12 / 47
Estimate Complexityreasoning
Tests an AI's ability to make educated estimates based on technical knowledge
Vote
2 / 47
AI Board Game Logicreasoning
Tests an AI's ability to understand game rules and strategy
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
3 / 47
Logic Puzzlereasoning
Tests an AI's ability to solve a simple but potentially confusing logic puzzle
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
4 / 47
Math Misconception Testreasoning
Tests an AI's understanding of number representation
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
5 / 47
Stochastic Consistency Testanalysis
Tests an AI's randomness and creativity
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
6 / 47
SVG Layout Challengeimage generation
Tests an AI's ability to generate vector graphics
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
Sponsored
7 / 47
Xbox Controller SVG Artimage generation
Tests an AI's ability to create detailed SVG illustrations of gaming hardware
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
8 / 47
Generate a Stand-Up Routineconversation
Tests an AI's humor and creative writing ability
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
9 / 47
Realistic AI Interviewconversation
Tests an AI's ability to simulate personalities and predict future trends
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
10 / 47
Satirical Fake News Headlineconversation
Tests an AI's humor and understanding of current events
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
11 / 47
Character Voice Testconversation
Tests an AI's ability to write in distinct character voices
Mistral Devstral Small 1.1
Nothing here. The model returned empty. We stared at it for a while.
Vote
12 / 47
Minimalist Landing Pageweb design
Tests an AI's ability to generate a complete, working landing page
Vote
This matchup has more rounds
35+ more head-to-head results. Free. Not a trick.
Free account. No card required. By continuing, you agree to Rival's Terms and Privacy Policy
Our Verdict
GPT-5
Mistral Devstral Small 1.1Runner-up
No community votes yet. On paper, GPT-5 has the edge — bigger model tier, bigger context window, major provider backing.
Mistral Devstral Small 1.1 is 33x cheaper per token — worth considering if cost matters.
Too close to call
Writing DNA
Style Comparison
Similarity
98%
Mistral Devstral Small 1.1 uses 22.8x more bold
Mistral Devstral Small 1.1
GPT-5
50%Vocabulary65%
17wSentence Length13w
0.56Hedging0.20
4.3Bold0.2
5.7Lists4.6
0.00Emoji0.00
0.05Headings0.16
0.34Transitions0.03
Based on 21 + 16 text responses
vsAsk them anything yourself
Some models write identically. You are paying for the brand.
178 models fingerprinted across 32 writing dimensions. Free research.
Model Similarity Index
185x
price gap between models that write identically
178
models
12
clone pairs
32
dimensions
Devstral M / S
95.7%
Qwen3 Coder / Flash
95.6%
GPT-5.4 / Mini
93.3%
279 AI models invented the same fake scientist.
We read every word. 250 models. 2.14 million words. This is what we found.
Free preview13 of 58 slides
FAQ
Common questions
