Claude 3.7 Sonnet vs GPT OSS 120B
Compare Claude 3.7 Sonnet by Anthropic against GPT OSS 120B by OpenAI, in 16 community votes, gpt oss 120b wins 55% of head-to-head duels, context windows of 200K vs 131K, tested across 54 shared challenges.
Reasoning: GPT OSS 120B wins 83% of votes
Image Generation: Claude 3.7 Sonnet wins 67% of votes
Our Verdict
GPT OSS 120BWinner
Claude 3.7 SonnetRunner-up
GPT OSS 120B has the edge overall. In 16 blind votes, GPT OSS 120B wins 55% of the time.
Pick Claude 3.7 Sonnet for Image Generation. Pick GPT OSS 120B for Reasoning. GPT OSS 120B is 19x cheaper per token — worth considering if cost matters.
Slight edge
API pricing
Cost per 1M tokens
Claude 3.7 Sonnet
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
24%
GPT OSS 120B uses 15.4x more emoji
Claude 3.7 Sonnet
GPT OSS 120B
62%Vocabulary52%
35wSentence Length19w
0.99Hedging0.28
1.2Bold7.4
4.3Lists1.8
0.00Emoji0.15
1.78Headings0.73
0.23Transitions0.17
Based on 13 + 21 text responses
Research
What we learned reading every model
FAQ
