Claude Sonnet 3.6 (2022-10-22) vs GPT-5.1-Codex
Compare Claude Sonnet 3.6 (2022-10-22) by Anthropic against GPT-5.1-Codex by OpenAI, context windows of 200K vs 400K, tested across 53 shared challenges.
Our Verdict
GPT-5.1-Codex
Claude Sonnet 3.6 (2022-10-22)Runner-up
No community votes yet. On paper, GPT-5.1-Codex has the edge — bigger model tier, newer, bigger context window.
Slight edge
API pricing
Cost per 1M tokens
Claude Sonnet 3.6 (2022-10-22)
Input
$3.00
Output
$15.00
GPT-5.1-Codex
Input
$1.25
2.4× cheaper
Output
$10.00
1.5× cheaper
GPT-5.1-Codex is cheaper on both — 2.4× input, 1.5× output
Writing DNA
Style Comparison
Similarity
57%
GPT-5.1-Codex uses 10.3x more bold
Claude Sonnet 3.6 (2022-10-22)
GPT-5.1-Codex
66%Vocabulary70%
74wSentence Length17w
0.72Hedging0.39
0.3Bold3.4
8.9Lists3.5
0.00Emoji0.00
0.06Headings0.50
0.09Transitions0.38
Based on 21 + 14 text responses
Research
What we learned reading every model
FAQ
