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 April 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
GPT-5 Codex
Claude 3.7 Sonnet
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
Writing DNA

Style Comparison

Similarity
93%

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
vs

Ask them anything yourself

Claude 3.7 SonnetGPT-5 Codex

279 AI models invented the same fake scientist.

We read every word. 250 models. 2.14 million words. This is what we found.

AI Hallucination Index 2026
Free preview13 of 58 slides
FAQ

Common questions