Claude 2 vs GPT OSS 120B
Compare Claude 2 by Anthropic against GPT OSS 120B by OpenAI, context windows of 100K vs 131K, tested across 5 shared challenges.
Our Verdict
GPT OSS 120B
Claude 2Runner-up
No community votes yet. On paper, GPT OSS 120B has the edge — bigger model tier, newer.
GPT OSS 120B is 41x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
Claude 2
Input
$11.02
Output
$32.68
GPT OSS 120B
Input
$0.18
61× cheaper
Output
$0.80
41× cheaper
GPT OSS 120B is cheaper on both — 61× input, 41× output
Writing DNA
Style Comparison
Similarity
30%
GPT OSS 120B uses 27.6x more hedging
Claude 2
GPT OSS 120B
65%Vocabulary52%
13wSentence Length19w
0.00Hedging0.28
0.0Bold7.4
10.2Lists1.8
0.00Emoji0.15
0.00Headings0.73
0.00Transitions0.17
Based on 2 + 21 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
