Normie ModeBest AI for writing
Emails, articles, reports, stories and editing.
Get it with Claude Pro, $20 a month
Top of 14 models for this task
4th and 5th of 14 models for this task
Keep in mind Based on people's votes only.
Based only on people's votes. The picks follow a fixed rule using the charts below and each app's plans.
Norm's guide
What I'd tell a friend who asked.
What AI is good at
- Getting you past a blank page.
- Tidying up grammar and tone.
- Shortening long text.
Where it trips up
- Sounding bland or overly formal.
- Adding details you didn't ask for.
- Losing your own voice.
How to get a good result
- Tell it who the reader is and what you want them to do.
- Give it an example of your own writing to match.
- Edit the result. Don't just paste it.
How the models compare
Every model we could score for writing, combining the tests below.
Overall for writing
Position on a combined score from 3 tests. The longer the bar, the further ahead · Higher is better
On the tests we have, Claude Opus 5.5 comes out on top, followed by Claude Fable 5.1 and Gemini 3.8 Flash.
The evidence
People's votes on writing and language
Tests this task · People compared two anonymous answers to writing, editing and language questions. · Higher is better
Claude Opus 5.5 and Claude Fable 5.1 are neck and neck at the top, followed by Gemini 3.8 Flash and Gemini 3.1 Pro; Claude Fable 5.1 costs about 3 times as much.
People's votes on creative writing
Tests this task · People compared two anonymous pieces of creative writing. · Higher is better
Claude Opus 5.5 and Claude Fable 5.1 are neck and neck at the top, followed by Gemini 3.8 Flash and Gemini 3.1 Pro; Claude Fable 5.1 costs about 3 times as much.
People's votes on following instructions
Tests a related skill · People compared two anonymous answers to requests with specific instructions. · Higher is better
Claude Opus 5.5 and Claude Fable 5.1 are neck and neck at the top, followed by Gemini 3.8 Flash and Kimi K3; Claude Fable 5.1 costs about 3 times as much.
If you build with it
What the makers charge developers who use the models directly. Using an app? The plans above are what you pay.
Cost per 1,000 typical requests
List price, about 1,500 words in and 500 out per request · Lower is better
GPT-6 Luna is cheapest, followed by DeepSeek V4.1 Flash and GPT-5.6 Luna.