PodcastIntelligence Snacks · Weekly conversations about AI, software and business, from the team behind Normie Mode.Listen →
Tests explained · People's votes

People's votes on writing and language

People compared two anonymous answers to writing, editing and language questions.

Run by

LMArena

How to read it

A rating from thousands of head-to-head votes. Higher means people preferred its answers more often. The thin line is the likely range.

Used for

9 tasks on this site.

How the models did

Rating from blind votes · 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 Opus 5.5 · Anthropic1st
Claude Fable 5.1 · Anthropic2nd
Gemini 3.8 Flash · Google DeepMind3rd
Gemini 3.1 Pro · Google DeepMind4th
Kimi K3 · Moonshot AI5th
Gemini 3.6 Flash · Google DeepMind6th
GPT-5.6 Sol · OpenAI7th
DeepSeek V4.1 Flash · DeepSeek8th
DeepSeek V4 Pro · DeepSeek9th
GPT-6 Astra · OpenAI10th
Claude Sonnet 5 · Anthropic11th
Gemini 3.5 Flash-Lite · Google DeepMind12th
GPT-5.6 Luna · OpenAI13th
Claude Haiku 4.5 · Anthropic14th
GPT-6 Luna · OpenAINot tested yet
GPT-6 Sol · OpenAINot tested yet
Source: LMArena · votes as of 25 Sept 2026

Where we use it

Each task page labels this test by how closely it matches the task.

TaskHow close
Best AI for writingTests this task
Best AI for scripts and content creationTests this task
Best AI for writing a bookTests a related skill
Best AI for creative writingTests a related skill
Best AI for essays and academic writingTests this task
Best AI for teachersTests a related skill
Best AI for CVs, job applications and interviewsTests a related skill
Best AI for marketingTests a related skill
Best AI for presentations and PowerPointTests a related skill
Intelligence Snacks newsletter

The big AI ideas each week, in your inbox