Mistral Devstral Small 1.1 vs Kimi Linear 48B A3B Instruct
Compare Mistral Devstral Small 1.1 by Mistral AI against Kimi Linear 48B A3B Instruct by Moonshot AI, tested across 35 shared challenges.
Our Verdict
Kimi Linear 48B A3B Instruct
Mistral Devstral Small 1.1Runner-up
No community votes yet. On paper, Kimi Linear 48B A3B Instruct has the edge — bigger model tier, newer, bigger context window.
Too close to call
API pricing
Cost per 1M tokens
Mistral Devstral Small 1.1
Input
$0.10
3.0× cheaper
Output
$0.30
2.0× cheaper
Kimi Linear 48B A3B Instruct
Input
$0.30
Output
$0.60
Mistral Devstral Small 1.1 is cheaper on both — 3.0× input, 2.0× output
Writing DNA
Style Comparison
Similarity
31%
Kimi Linear 48B A3B Instruct uses 7.8x more headings
Mistral Devstral Small 1.1
Kimi Linear 48B A3B Instruct
50%Vocabulary63%
17wSentence Length15w
0.56Hedging0.19
4.3Bold5.2
5.7Lists3.2
0.00Emoji0.00
0.05Headings0.38
0.34Transitions0.05
Based on 21 + 14 text responses
Research
What we learned reading every model
FAQ
