Claude 3 Opus vs GPT-5 Codex
Compare Claude 3 Opus by Anthropic against GPT-5 Codex by OpenAI, tested across 11 shared challenges. Updated June 2026.
Which is better, Claude 3 Opus or GPT-5 Codex?
Claude 3 Opus and GPT-5 Codex are both competitive models. Compare their real outputs side by side below.
Key Differences Between Claude 3 Opus and GPT-5 Codex
Claude 3 Opus is made by anthropic while GPT-5 Codex is from openai.
Our Verdict
Claude 3 Opus
GPT-5 Codex
No community votes yet. On paper, these are closely matched - try both with your actual task to see which fits your workflow.
Too close to call
API pricing
Cost per 1M tokens
Claude 3 Opus
Input
$15.00
Output
$75.00
GPT-5 Codex
Input
—
Output
—
Writing DNA
Style Comparison
Similarity
58%
GPT-5 Codex uses 229.7x more bold
Claude 3 Opus
GPT-5 Codex
54%Vocabulary64%
14wSentence Length17w
0.48Hedging0.38
0.0Bold2.3
3.0Lists3.5
0.00Emoji0.15
0.00Headings0.49
0.06Transitions0.05
Based on 3 + 13 text responses
Research
What we learned reading every model
FAQ
Common questions
Keep exploring
