Claude Sonnet 3.6 (2022-10-22) vs GPT OSS 120B
Compare Claude Sonnet 3.6 (2022-10-22) by Anthropic against GPT OSS 120B by OpenAI, context windows of 200K vs 131K, tested across 54 shared challenges.
Our Verdict
GPT OSS 120B
Claude Sonnet 3.6 (2022-10-22)Runner-up
No community votes yet. On paper, GPT OSS 120B has the edge — bigger model tier, newer.
GPT OSS 120B is 19x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
Claude Sonnet 3.6 (2022-10-22)
Input
$3.00
Output
$15.00
GPT OSS 120B
Input
$0.18
17× cheaper
Output
$0.80
19× cheaper
GPT OSS 120B is cheaper on both — 17× input, 19× output
Writing DNA
Style Comparison
Similarity
28%
GPT OSS 120B uses 15.4x more emoji
Claude Sonnet 3.6 (2022-10-22)
GPT OSS 120B
66%Vocabulary52%
74wSentence Length19w
0.72Hedging0.28
0.3Bold7.4
8.9Lists1.8
0.00Emoji0.15
0.06Headings0.73
0.09Transitions0.17
Based on 21 + 21 text responses
Research
What we learned reading every model
FAQ
