Mistral Devstral Small 1.1 vs GPT OSS 120B
Compare Mistral Devstral Small 1.1 by Mistral AI against GPT OSS 120B by OpenAI, tested across 54 shared challenges.
Our Verdict
GPT OSS 120B
Mistral Devstral Small 1.1Runner-up
No community votes yet. On paper, GPT OSS 120B has the edge — bigger model tier, bigger context window, major provider backing.
Too close to call
API pricing
Cost per 1M tokens
Mistral Devstral Small 1.1
Input
$0.10
1.8× cheaper
Output
$0.30
2.7× cheaper
GPT OSS 120B
Input
$0.18
Output
$0.80
Mistral Devstral Small 1.1 is cheaper on both — 1.8× input, 2.7× output
Writing DNA
Style Comparison
Similarity
40%
GPT OSS 120B uses 15.4x more emoji
Mistral Devstral Small 1.1
GPT OSS 120B
50%Vocabulary52%
17wSentence Length19w
0.56Hedging0.28
4.3Bold7.4
5.7Lists1.8
0.00Emoji0.15
0.05Headings0.73
0.34Transitions0.17
Based on 21 + 21 text responses
Research
What we learned reading every model
FAQ
