Mistral Devstral Small 1.1 vs MiniMax M2.5
Compare Mistral Devstral Small 1.1 by Mistral AI against MiniMax M2.5 by MiniMax, tested across 53 shared challenges.
Our Verdict
MiniMax M2.5
Mistral Devstral Small 1.1Runner-up
No community votes yet. On paper, MiniMax M2.5 has the edge — bigger model tier, newer, bigger context window.
Mistral Devstral Small 1.1 is 4.0x 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
3.0× cheaper
Output
$0.30
4.0× cheaper
MiniMax M2.5
Input
$0.30
Output
$1.20
Mistral Devstral Small 1.1 is cheaper on both — 3.0× input, 4.0× output
Writing DNA
Style Comparison
Similarity
53%
MiniMax M2.5 uses 1.5x more emoji
Mistral Devstral Small 1.1
MiniMax M2.5
50%Vocabulary55%
17wSentence Length25w
0.56Hedging0.58
4.3Bold6.0
5.7Lists4.4
0.00Emoji0.01
0.05Headings1.11
0.34Transitions0.16
Based on 21 + 23 text responses
Research
What we learned reading every model
FAQ
