Best AI for job applications and CVs

As of 2026-07-18, Anthropic: Claude Opus 4.8 (Fast) is the strongest model for this task in our daily benchmark, where over 350 AI models are evaluated and the best are presented.

An AI-written application is easy to spot — and recruiters read a lot of them. The value is not in letting the model write the letter for you, but in using it to tighten your own.

For application text we rank by language quality, since a letter with anglicisms or a stiff tone is dismissed immediately. Ranked by language score, from today’s benchmark.

Runner-up
Anthropic: Claude Haiku 4.5
anthropic
Score: 8.0/10
Language: 9.3/10
Speed: 113 t/s
$1.00
Third choice
Google: Gemma 3 4B
google
Score: 8.0/10
Language: 9.3/10
Speed: 237 t/s
$0.05

Today’s ranking

Model Provider Score Language Speed Input price/1M
Anthropic: Claude Opus 4.8 (Fast) anthropic 8.3/10 9.3/10 131 t/s $10.00
Anthropic: Claude Haiku 4.5 anthropic 8.0/10 9.3/10 113 t/s $1.00
Google: Gemma 3 4B google 8.0/10 9.3/10 237 t/s $0.05
Cohere: Command R+ (08-2024) cohere 7.5/10 9.3/10 160 t/s $2.50
Perplexity: Sonar Pro perplexity 7.7/10 9.0/10 68 t/s $3.00
Meta: Llama 3.1 8B Instruct meta-llama 5.2/10 9.0/10 392 t/s $0.05
Mistral: Mistral Small 3 mistralai 7.8/10 8.7/10 234 t/s $0.05
IBM: Granite 4.0 Micro ibm-granite 5.4/10 8.3/10 179 t/s $0.02

Use AI as an editor, not an author

Write the draft yourself, in your own voice, and ask the model to cut repetition, tighten sentences and flag claims you have not backed up. That keeps what makes the application yours — concrete experience and examples — and removes only the filler.

What the recruiter sees through

Phrases like “passionate about”, “dynamic environment” and “unique combination of skills” are the default output of a model that was given nothing concrete to work with. Give it the job ad, your CV and three real examples from your work, and the text becomes specific enough to stand out.

hvilkenAI is independent. We have no affiliate agreements, sponsored placements or commercial ties to the AI providers we test. Every recommendation rests on test results alone.

Frequently asked questions

Is it cheating to use AI for a job application?
No, no more than asking a friend to proofread. But the content has to be yours and true — experience you do not have should not appear.
Can recruiters tell an application is AI-written?
Often yes, if the text is generic. What gives it away is the absence of concrete detail, not the language itself.
Should I use AI for my CV too?
For tightening phrasing and surfacing results instead of duties, yes. For inventing content, no.
Which model is best for this?
The ranking above comes from today’s benchmark, where we evaluate over 350 models and present the strongest on the language.

Other tasks

Doing something else? See which model is best for it.

→ Other tasks

Read also

← Back to home