Mistral Devstral Small 1.1 vs Qwen: Qwen3 235B A22B Thinking 2507
Compare Mistral Devstral Small 1.1 by Mistral AI against Qwen: Qwen3 235B A22B Thinking 2507 by Qwen, tested across 55 shared challenges.
Our Verdict
Qwen: Qwen3 235B A22B Thinking 2507
Mistral Devstral Small 1.1Runner-up
No community votes yet. On paper, Qwen: Qwen3 235B A22B Thinking 2507 has the edge — bigger model tier, bigger context window.
Too close to call
API pricing
Cost per 1M tokens
Mistral Devstral Small 1.1
Input
$0.10
1.1× cheaper
Output
$0.30
2.0× cheaper
Qwen: Qwen3 235B A22B Thinking 2507
Input
$0.11
Output
$0.60
Mistral Devstral Small 1.1 is cheaper on both — 1.1× input, 2.0× output
Writing DNA
Style Comparison
Similarity
44%
Qwen: Qwen3 235B A22B Thinking 2507 uses 53.9x more emoji
Mistral Devstral Small 1.1
Qwen: Qwen3 235B A22B Thinking 2507
50%Vocabulary56%
17wSentence Length14w
0.56Hedging0.37
4.3Bold5.7
5.7Lists4.0
0.00Emoji0.54
0.05Headings0.70
0.34Transitions0.14
Based on 21 + 22 text responses
Research
What we learned reading every model
FAQ
