GPT-5 Codex vs Qwen Plus 0728 (thinking)

Compare GPT-5 Codex by OpenAI against Qwen Plus 0728 (thinking) by Qwen, tested across 36 shared challenges. Updated April 2026.

Which is better, GPT-5 Codex or Qwen Plus 0728 (thinking)?

GPT-5 Codex and Qwen Plus 0728 (thinking) are both competitive models. Compare their real outputs side by side below.

Key Differences Between GPT-5 Codex and Qwen Plus 0728 (thinking)

GPT-5 Codex is made by openai while Qwen Plus 0728 (thinking) is from qwen.

Our Verdict
GPT-5 Codex
GPT-5 Codex
Qwen Plus 0728 (thinking)
Qwen Plus 0728 (thinking)Runner-up

No community votes yet. On paper, GPT-5 Codex has the edge — bigger model tier, major provider backing.

Too close to call
Writing DNA

Style Comparison

Similarity
99%

Qwen Plus 0728 (thinking) uses 3.1x more bold

GPT-5 Codex
Qwen Plus 0728 (thinking)
64%Vocabulary54%
17wSentence Length15w
0.38Hedging0.36
2.3Bold7.0
3.5Lists4.6
0.15Emoji0.34
0.49Headings0.94
0.05Transitions0.09
Based on 13 + 18 text responses
vs

Ask them anything yourself

GPT-5 CodexQwen Plus 0728 (thinking)

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