Mistral Devstral Small 1.1 vs Gemini 2.5 Flash Preview (thinking)
Compare Mistral Devstral Small 1.1 by Mistral AI against Gemini 2.5 Flash Preview (thinking) by Google AI, tested across 20 shared challenges.
Our Verdict
Gemini 2.5 Flash Preview (thinking)
Mistral Devstral Small 1.1Runner-up
No community votes yet. On paper, Gemini 2.5 Flash Preview (thinking) has the edge — bigger model tier, bigger context window, major provider backing.
Mistral Devstral Small 1.1 is 12x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
Mistral Devstral Small 1.1
Input
$0.10
1.7× cheaper
Output
$0.30
12× cheaper
Gemini 2.5 Flash Preview (thinking)
Input
$0.17
Output
$3.50
Mistral Devstral Small 1.1 is cheaper on both — 1.7× input, 12× output
Writing DNA
Style Comparison
Similarity
62%
Mistral Devstral Small 1.1 uses 4.8x more headings
Mistral Devstral Small 1.1
Gemini 2.5 Flash Preview (thinking)
50%Vocabulary53%
17wSentence Length14w
0.56Hedging0.38
4.3Bold4.4
5.7Lists4.1
0.00Emoji0.00
0.05Headings0.00
0.34Transitions0.24
Based on 21 + 7 text responses
Research
What we learned reading every model
FAQ
