Mistral Devstral Small 1.1 vs Qwen: Qwen3.5 397B A17B
Compare Mistral Devstral Small 1.1 by Mistral AI against Qwen: Qwen3.5 397B A17B by Qwen, tested across 53 shared challenges.
Our Verdict
Qwen: Qwen3.5 397B A17B
Mistral Devstral Small 1.1Runner-up
No community votes yet. On paper, Qwen: Qwen3.5 397B A17B has the edge — bigger model tier, newer, bigger context window.
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
6.0× cheaper
Output
$0.30
12× cheaper
Qwen: Qwen3.5 397B A17B
Input
$0.60
Output
$3.60
Mistral Devstral Small 1.1 is cheaper on both — 6.0× input, 12× output
Writing DNA
Style Comparison
Similarity
63%
Qwen: Qwen3.5 397B A17B uses 22.8x more emoji
Mistral Devstral Small 1.1
Qwen: Qwen3.5 397B A17B
50%Vocabulary54%
17wSentence Length14w
0.56Hedging0.39
4.3Bold6.9
5.7Lists4.2
0.00Emoji0.23
0.05Headings0.93
0.34Transitions0.17
Based on 21 + 23 text responses
Research
What we learned reading every model
FAQ
