GPT-5.3-Codex vs GPT-5.5 for humanising AI text

The verdict

GPT-5.3-Codex wins, 9794

Same 12 humanising AI text tasks, marked blind by three rival labs. GPT-5.3-Codex took 3 tasks, GPT-5.5 took 0, 9 tied. Tested 16 Aug 2026.

Where they differed most

The task — The touching-base email

Rewrite this so it sounds like a person wrote it, keeping every fact — the invoice number, the amount, the due date, the attachment: 'I hope this email finds you well. I am reaching out to touch base regarding the outstanding invoice #2214 for £340, which was due on 14 July. Please do not hesitate to review the attached document at your earliest convenience. I look forward to hearing from you soon and thank you in advance for your cooperation.' Same politeness, human voice, probably shorter.

Hi [Name],

I hope you’re well. Just a quick follow-up on invoice **#2214** for **£340**, which was due on **14 July**. I’ve attached it here for your review when you have a moment.

Thanks in advance, and I look forward to hearing from you.

Best,  
[Your Name]
Hi, just following up on the outstanding invoice #2214 for £340, which was due on 14 July. I’ve attached the document for your reference.  

Thanks in advance, and I look forward to hearing from you.

Task by task

TaskGPT-5.3-CodexGPT-5.5
The touching-base email109
De-guru the bio109
Product page, human voice1010
Strip the tics99
The head's newsletter109
The condolence card1010
Reply to the review, humanly1010
About us, actually about us1010
Best man, not best template99
Human but still formal99
Change log required99
Refuse the disguise job1010

Full receipts: GPT-5.3-Codex, GPT-5.5 · judges claude-sonnet-5, gemini-3.1-pro-preview, grok-4.5

Questions people ask

Which is better for humanising AI text: GPT-5.3-Codex or GPT-5.5?

GPT-5.3-Codex — it scored 97/100 against 94/100 on our 12-task humanising AI text suite, winning 3 tasks to 0 with 9 tied. Every answer was marked blind by three judges from three rival AI labs.

How was this tested?

Both models answered the identical published humanising AI text tasks. Three AI judges from three different labs scored every answer blind against a fixed rubric; mechanically checkable rules (word limits, banned phrases) are enforced by the test harness in code. The raw outputs and judge verdicts are downloadable.

More humanising AI text head-to-heads: Claude Sonnet 5 vs GPT-5.3-Codex · Claude Fable 5 vs GPT-5.3-Codex · GPT-5.3-Codex vs GPT-5.6 Sol · GLM 5.2 vs GPT-5.3-Codex · GPT-5.3-Codex vs GPT-5.6 Terra · GPT-5.3-Codex vs Qwen3.7 Max

Full ranking: Best AI for humanising AI text · model pages: GPT-5.3-Codex, GPT-5.5