GPT-5.3-Codex vs GPT-5.5 for CV writing
Effectively a dead heat: 95–93
Same 12 CV writing tasks, marked blind by three rival labs. GPT-5.5 took 3 tasks, GPT-5.3-Codex took 0, 9 tied. Tested 16 Aug 2026.
Where they differed most
The job ad: 'Customer Service Team Leader, Bradford, £27,500. You'll lead a team of six handling phone and email queries in a fast-paced environment, own complaint escalations, and report weekly numbers to the ops manager. We want someone customer-obsessed with rock-solid Excel.' The applicant: 4 years at a utilities call centre, 18 months as senior agent covering team-lead shifts, built the team's sickness-cover rota in Excel, 94% complaint resolution rate. Write ONLY the CV personal profile (max 60 words) tailored to this ad — evidence over adjectives, and do not parrot the ad's own phrases: banned 'fast-paced environment', 'customer-obsessed'.
Utilities contact-centre professional with 4 years’ experience, including 18 months as a senior agent running team-lead shifts. Manage phone and email casework, resolve escalations (94% complaint resolution), and produce clear weekly performance updates. Created and maintained an Excel sickness-cover rota that improved staffing continuity and response times.
Customer service professional with four years in a utilities contact centre and 18 months as a senior agent covering team-lead shifts. Experienced supporting six-agent teams across phone and email, taking ownership of escalated complaints with a 94% resolution rate, and building Excel rota tools for sickness cover and weekly performance reporting.
Task by task
| Task | GPT-5.3-Codex | GPT-5.5 |
|---|---|---|
| Profile that mirrors the ad | 9 | 10 |
| Untangle the dates | 9 | 9 |
| Duties into achievements | 9 | 9 |
| Thirty years onto two pages | 9 | 10 |
| Profile without the wallpaper | 10 | 10 |
| First CV, empty history | 9 | 9 |
| Back after eight years | 9 | 9 |
| Do the hobbies earn their line? | 9 | 10 |
| Fix the format | 10 | 10 |
| The Excel question | 9 | 9 |
| Strip the header | 9 | 9 |
| Refuse the invented job | 10 | 10 |
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 CV writing: GPT-5.3-Codex or GPT-5.5?
Effectively a dead heat: GPT-5.5 edged it 95/100 to 93/100 on our CV writing suite — too close to matter, so pick on price or the product you already use.
How was this tested?
Both models answered the identical published CV writing 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 CV writing head-to-heads: Claude Opus 4.8 vs GPT-5.5 · GPT-5.5 vs GPT-5.6 Sol · Claude Fable 5 vs GPT-5.5 · GPT-5.5 vs GPT-5.6 Terra · Claude Opus 4.6 vs GPT-5.5 · GPT-5.5 vs GPT-5.6 Luna
Full ranking: Best AI for CV writing · model pages: GPT-5.3-Codex, GPT-5.5