Claude 3.7 Sonnet vs GPT-5 Codex
Compare Claude 3.7 Sonnet by Anthropic against GPT-5 Codex by OpenAI, tested across 50 shared challenges. Updated June 2026.
Which is better, Claude 3.7 Sonnet or GPT-5 Codex?
Claude 3.7 Sonnet and GPT-5 Codex are both competitive models. Compare their real outputs side by side below.
Key Differences Between Claude 3.7 Sonnet and GPT-5 Codex
Claude 3.7 Sonnet is made by anthropic while GPT-5 Codex is from openai.
Our Verdict
GPT-5 Codex
Claude 3.7 SonnetRunner-up
No community votes yet. On paper, GPT-5 Codex has the edge — bigger model tier, newer.
Too close to call
API pricing
Cost per 1M tokens
Claude 3.7 Sonnet
Input
$3.00
Output
$15.00
GPT-5 Codex
Input
—
Output
—
Writing DNA
Style Comparison
Similarity
56%
GPT-5 Codex uses 14.6x more emoji
Claude 3.7 Sonnet
GPT-5 Codex
62%Vocabulary64%
35wSentence Length17w
0.99Hedging0.38
1.2Bold2.3
4.3Lists3.5
0.00Emoji0.15
1.78Headings0.49
0.23Transitions0.05
Based on 13 + 13 text responses
Research
What we learned reading every model
FAQ
