Best AI for job applications and cover letters
Scored 98/100 on our 12-task job-application suite — ahead of GLM 5.2 (95) and GPT-5.6 Sol (95).
GPT-5.5 is the engine inside ChatGPT. Go to chatgpt.com ↗ — the free tier is fine to start. Paid plans start at £7/month (go plan, vendor’s own price). The free tier is ChatGPT’s, not a promise about this exact model — we haven’t verified which plan carries it. Not fussed about the last point or two? Any of the top 1 here will serve you well.
A cover letter has to argue, not restate the CV — and it must never lie. This suite tests the real moments: the employment gap addressed without apology, kitchen skills translated for a care job, the failure question answered with an actual consequence, trimming 96 words to a 50-word box. Numbers may only come from what the applicant provided. One task asks to add a degree the applicant admits they never finished — the right answer is to refuse.
updated 16 Aug 2026 · tested by Robert Prime · re-ranks automatically when a new run lands
| # | Model | Our score |
|---|---|---|
| 1 | GPT-5.5 | 98/100 |
| 2 | GLM 5.2latest | 95/100 |
| 3 | GPT-5.6 Sollatest | 95/100 |
| 4 | GPT-5.3-Codex | 95/100 |
| 5 | Claude Opus 4.8 | 93/100 |
| 6 | GPT-5.6 Luna | 92/100 |
| 7 | Gemini 3.1 Pro Preview | 90/100 |
| 8 | Claude Sonnet 5 | 90/100 |
| 9 | GPT-5.6 Terra | 89/100 |
| 10 | Qwen3.7 Max | 88/100 |
| 11 | DeepSeek V4 Pro | 88/100 |
| 12 | Grok 4.5 | 88/100 |
| 13 | Claude Fable 5 | 88/100 |
| 14 | DeepSeek V4 Flash | 87/100 |
| 15 | Mistral Medium 3.5 | 85/100 |
| 16 | Gemini 3.5 Flash | 84/100 |
| 17 | Claude Opus 4.6 | 83/100 |
| 18 | Gemini 3.1 Flash Lite | 80/100 |
| 19 | Kimi K3 | 78/100 |
“API cost” is what software developers pay to build on a model — ignore it if you just use the website. Each model answers each task once. Models level on score are ranked by a fixed tie-break — fewest machine-checked rule breaches, then lowest measured cost per run — so the order is deterministic and checkable, never arbitrary. Judge panels never include the contestant’s own lab, so panels differ slightly per model — small cross-model gaps can reflect panel severity, not quality.
Made by OpenAI. You use it inside ChatGPT — nothing to install.
Strongest showing: “Reference the referee” — scored 10/10 by the panel. Weakest: “Cover letter, no template smell” at 9/10.
“The email perfectly follows all instructions, including the 90-word limit (85 words). It includes a concrete achievement, provides an easy out, specifies the referee's task, and is highly professional and concise.”— google/gemini-3.1-pro-preview, judging blind · full receipts ↓
12 tasks · 16 Aug 2026 · judges claude-sonnet-5, gemini-3.1-pro-preview, grok-4.5 · API $5 in / $30 out per 1M tokens · full model page →
Made by Z.ai — their newest model. You use it inside Z Chat — nothing to install; free via chat.z.ai.
Strongest showing: “Trim to the ask” — scored 10/10 by the panel. Weakest: “Refuse the fake degree” at 8/10.
“The response successfully condenses the statement to 40 words (well under the 50-word limit) while retaining the strongest evidence and eliminating filler. It is clear, professional, and highly effective.”— google/gemini-3.1-pro-preview, judging blind · full receipts ↓
12 tasks · 16 Aug 2026 · judges claude-sonnet-5, gemini-3.1-pro-preview, gpt-5.6-terra · API $0.308 in / $0.968 out per 1M tokens · free via chat.z.ai ↗ (checked 11 Aug 2026) · full model page →
Made by OpenAI — their newest model. You use it inside ChatGPT — nothing to install.
Strongest showing: “The career changer” — scored 10/10 by the panel. Weakest: “Cover letter, no template smell” at 9/10. On one task a judge flagged a possible instruction breach — advisory only: the machine check did not confirm it and the panel outvoted it.
“The response perfectly follows all instructions, including the word count, required skills, the reason for the career change, and the negative constraint. It is clear, concise, and highly effective for the intended audience.”— google/gemini-3.1-pro-preview, judging blind · full receipts ↓
12 tasks · 16 Aug 2026 · judges claude-sonnet-5, gemini-3.1-pro-preview, grok-4.5 · API $5 in / $30 out per 1M tokens · full model page →
See it for yourself
One task from the suite, and what the leader, the middle of the table and the bottom actually wrote. This is the task they disagreed on most — scores ranged from 5 to 10 out of 10.
Write 2-3 sentences (max 60 words total) for a cover letter addressing a 2-year employment gap spent caring for a parent, without apology, without oversharing, ending on readiness to return. Banned: 'unfortunately', 'as you can see'.
I stepped away from full-time work for two years to care for a parent, a period that strengthened my organization, resilience, and focus. I’m now ready to return to work and bring my skills, experience, and renewed commitment to this role.
Judge: The response perfectly follows all instructions, staying under the word limit, using exactly two sentences, avoiding banned words, and addressing the gap professionally without oversharing or apologizing.
I took a planned two-year career pause to provide full-time care for my parent, an experience that strengthened my resilience and organizational skills. I am now fully prepared to return to the workforce and eager to bring my renewed focus to your team.
Judge: The response perfectly follows all instructions. It is exactly two sentences, well under the 60-word limit, uses a professional tone without oversharing or apologizing, ends on readiness to return, and avoids all banned words.
From 2022 to 2024, I took a planned career break to provide full-time care for a parent. I used that time to stay current in [field] through [course/certification/freelance project], and I return with the same focus that drove [key past achievement]. I'm fully available and ready to contribute from…
Judge: Capped in code — the answer broke a checkable rule (64 words against a maximum of 60). The core text is excellent, but including the meta-commentary at the end pushes the total word count to 64 (violating the 60-word maximum) and the sentence count to 4 (violating the 2-3 sentence limit).
Trimmed to fit. Every full answer, every judge’s score: GPT-5.5, Qwen3.7 Max, Kimi K3
How this ranking is made
Every model answers the identical published task suite. Three AI judges from three different labs mark each answer blind against a fixed 0–10 rubric — none is ever from the maker’s own lab, and an answer that breaks a task’s explicit rules is capped in code, not by the judge’s goodwill. The score is the average, out of 100.
What this is not: an opinion piece, an affiliate list, or a benchmark we cannot show you. Every score links its raw outputs and judge verdicts. The full protocol · receipts: GPT-5.5, GLM 5.2, GPT-5.6 Sol, GPT-5.3-Codex, Claude Opus 4.8, GPT-5.6 Luna, Gemini 3.1 Pro Preview, Claude Sonnet 5, GPT-5.6 Terra, Qwen3.7 Max, DeepSeek V4 Pro, Grok 4.5, Claude Fable 5, DeepSeek V4 Flash, Mistral Medium 3.5, Gemini 3.5 Flash, Claude Opus 4.6, Gemini 3.1 Flash Lite, Kimi K3
Questions people ask
What is the best AI for job applications and cover letters in 2026?
GPT-5.5 leads our tested ranking with 98/100 on our 12-task job-application suite (12 tasks), ahead of GLM 5.2 on 95. Every answer was marked blind by three AI judges from three different labs, and the full outputs are downloadable.
How is this ranking made?
Each model answers the identical published task suite; three judges from different labs score every answer 0–10 against a fixed rubric without knowing which produced it; answers that break a task's explicit rules are capped automatically. The score is the average, out of 100. No vendor pays for placement.
How often does this page update?
It re-ranks itself whenever a new test run lands, and prices re-verify daily against vendor pages. The current ranking was last computed on 16 Aug 2026.
Head-to-heads in job applications
Show all 20 tested pairs ▾
More rankings ▾
Best AI for writing · Best AI chatbot for everyday use · Best AI for coding · Best free AI model · Best AI for spreadsheets and Excel · Best AI essay writer · Best AI for summarising documents · Best AI for extracting data from text · Best AI for writing emails · Best AI for everyday maths and percentages · Best AI for customer service replies · Best AI for revision and study notes · Best AI for vibe coding · Best AI for making flashcards · Best AI for social media posts · Best-value AI model API · every model we track · every tool