Mistral Devstral Medium vs Gemini 3 Flash Preview
Compare Mistral Devstral Medium by Mistral AI against Gemini 3 Flash Preview by Google AI, tested across 55 shared challenges.
Our Verdict
Gemini 3 Flash Preview
Mistral Devstral MediumRunner-up
No community votes yet. On paper, Gemini 3 Flash Preview has the edge — bigger model tier, newer, bigger context window, major provider backing.
Slight edge
API pricing
Cost per 1M tokens
Mistral Devstral Medium
Input
$0.40
1.3× cheaper
Output
$2.00
1.5× cheaper
Gemini 3 Flash Preview
Input
$0.50
Output
$3.00
Mistral Devstral Medium is cheaper on both — 1.3× input, 1.5× output
Writing DNA
Style Comparison
Similarity
59%
Gemini 3 Flash Preview uses 4.4x more headings
Mistral Devstral Medium
Gemini 3 Flash Preview
50%Vocabulary55%
17wSentence Length18w
0.56Hedging0.42
4.5Bold7.1
5.3Lists4.5
0.00Emoji0.00
0.19Headings0.84
0.32Transitions0.07
Based on 21 + 24 text responses
Research
What we learned reading every model
FAQ
