GPT-5.1 Codex Max vs Qwen: Qwen3 235B A22B Thinking 2507
Compare GPT-5.1 Codex Max by OpenAI against Qwen: Qwen3 235B A22B Thinking 2507 by Qwen, tested across 53 shared challenges.
Our Verdict
GPT-5.1 Codex Max
Qwen: Qwen3 235B A22B Thinking 2507Runner-up
No community votes yet. On paper, GPT-5.1 Codex Max has the edge — newer, major provider backing.
Too close to call
API pricing
Cost per 1M tokens
GPT-5.1 Codex Max
Input
—
Output
—
Qwen: Qwen3 235B A22B Thinking 2507
Input
$0.11
Output
$0.60
Writing DNA
Style Comparison
Similarity
35%
Qwen: Qwen3 235B A22B Thinking 2507 uses 53.9x more emoji
GPT-5.1 Codex Max
Qwen: Qwen3 235B A22B Thinking 2507
60%Vocabulary56%
16wSentence Length14w
0.36Hedging0.37
2.3Bold5.7
4.2Lists4.0
0.00Emoji0.54
0.12Headings0.70
0.03Transitions0.14
Based on 13 + 22 text responses
Research
What we learned reading every model
FAQ
