Mistral Devstral Small 1.1 vs Llama 4 Maverick
Compare Mistral Devstral Small 1.1 by Mistral AI against Llama 4 Maverick by Meta AI, tested across 53 shared challenges.
Our Verdict
Llama 4 Maverick
Mistral Devstral Small 1.1Runner-up
No community votes yet. On paper, Llama 4 Maverick has the edge — bigger model tier, bigger context window, major provider backing.
Mistral Devstral Small 1.1 is 8.3x 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
15× cheaper
Output
$0.30
8.3× cheaper
Llama 4 Maverick
Input
$1.50
Output
$2.50
Mistral Devstral Small 1.1 is cheaper on both — 15× input, 8.3× output
Writing DNA
Style Comparison
Similarity
86%
Llama 4 Maverick uses 15.3x more headings
Mistral Devstral Small 1.1
Llama 4 Maverick
50%Vocabulary42%
17wSentence Length24w
0.56Hedging0.76
4.3Bold3.7
5.7Lists6.3
0.00Emoji0.00
0.05Headings0.74
0.34Transitions0.11
Based on 21 + 12 text responses
Research
What we learned reading every model
FAQ
