Claude 3 Opus vs GPT OSS 120B
Compare Claude 3 Opus by Anthropic against GPT OSS 120B by OpenAI, context windows of 200K vs 131K, tested across 12 shared challenges.
Our Verdict
Claude 3 Opus
GPT OSS 120B
No community votes yet. On paper, these are closely matched - try both with your actual task to see which fits your workflow.
GPT OSS 120B is 94x cheaper per token — worth considering if cost matters.
Too close to call
API pricing
Cost per 1M tokens
Claude 3 Opus
Input
$15.00
Output
$75.00
GPT OSS 120B
Input
$0.18
83× cheaper
Output
$0.80
94× cheaper
GPT OSS 120B is cheaper on both — 83× input, 94× output
Writing DNA
Style Comparison
Similarity
30%
GPT OSS 120B uses 743.4x more bold
Claude 3 Opus
GPT OSS 120B
54%Vocabulary52%
14wSentence Length19w
0.48Hedging0.28
0.0Bold7.4
3.0Lists1.8
0.00Emoji0.15
0.00Headings0.73
0.06Transitions0.17
Based on 3 + 21 text responses
Research
What we learned reading every model
FAQ
