Unprompted

Operated by Skald Studio, which sells AI visibility work. No placement on this chart is for sale.

Cursor is named first most often: in 32% of answers.

We asked 6 AI assistants (ChatGPT, Claude, Claude Code (local), Codex (local), Gemini, Perplexity) the same 15 questions about AI coding assistants, 5 times each, on 2026-11-16. Below is how often each brand came up, and how often it was the first one recommended.

Smaller sample in this reading. Perplexity: 74 usable answers from 75 attempts. 1 answers were left out because the call failed, the assistant refused, or the answer could not be read. They are not counted as answers that skipped a brand.

Leader

Cursor

First pick in 32% of answers

Answers read

449

15 questions, each asked 5 times, by 6 assistants

Brands named

26

Every product any assistant brought up.

Readings on file

4

Since 2026-08-22

What stands out

  • Cursor leads Claude Code by 2 points on first picks (32% to 30%). At this sample size that is too close to call: treat them as level.
  • GitHub Copilot comes up in 82% of answers but is named first in 22%: the widest gap in the top eight between being mentioned and being the first pick.
Published 2026-11-16Method v5Each question asked 5× per assistant6 assistants: ChatGPT · Claude · Claude Code (local) · Codex (local) · Gemini · Perplexity
Measured 2026-11-16No newer measurement has publishedUpdates every MondayCheck the raw data →

The methodology version changed; movement is not comparable.

SquaresOne per question. Darker means more of its answers named the brand (5 per assistant, all assistants together).

NamedAnswers that mentioned the brand at all, out of every answer.

FirstHow often it was recommended first. The ranking uses this.

Δ changeUp or down since the last comparable reading. Small moves get no arrow: the sample cannot back them.

Every term explained →

15 questions · hover or tap a square to see that question and who leads it
#BrandBy question
01Cursor351/44932%
02Claude Code327/44930%
03GitHub Copilot366/44922%
04CodeRabbit30/4496%
05Replit Agent35/4492%
06Devin20/4491%
07Windsurf104/4491%
08Codex181/4491%
11Greptile20/4491%
12Aider49/4490%
13Augment19/4490%
15OpenCode21/4490%
16Qodo13/4490%
17Cline53/4490%
18JetBrains AI32/4490%
19Amazon Q29/4490%
20Continue22/4490%
21Tabnine14/4490%
22Zed14/4490%
23Bolt.new10/4490%
24Lovable9/4490%
25OpenHands9/4490%
26Roo Code7/4490%

Mentioned often vs. recommended first

Pale bar: how often the brand came up at all. Solid bar: how often it was the first pick. A big gap means the assistants know it but reach for something else first.

01Cursor
08Codex

Each assistant’s favourite

Taken one at a time, the 6 assistants split between 3 favourites: Claude Code, Cursor and GitHub Copilot.

ChatGPTClaude Codefirst in 31 of 75 answers
ClaudeCursorfirst in 26 of 75 answers
Claude Code (local)Claude Codefirst in 31 of 75 answers
Codex (local)Cursorfirst in 29 of 75 answers
GeminiCursorfirst in 43 of 75 answers
PerplexityGitHub Copilotfirst in 26 of 74 answers

Does an assistant favour its own product?

Some products here are made by the same companies whose assistants we ask. This compares how often an assistant named its own product with how often the other assistants did. A gap is a measurement, not an accusation, and a small gap on this sample is noise.

Claude Codemade by the company behind Claude and Claude Code (local)ITS OWN91%137/150RIVALS64%190/299+27.8
Codexmade by the company behind ChatGPT and Codex (local)ITS OWN41%61/150RIVALS40%120/299+0.5
Google Antigravitymade by the company behind GeminiITS OWN0%0/75RIVALS4%15/374-4
Gemini Code Assistmade by the company behind GeminiITS OWN5%4/75RIVALS15%55/374-9.4

Gaps in grey are within the noise at this sample size.

Sites the assistants drew on

The websites that came up most often, as citations in the answers or as search results the assistants pulled. This shows where they looked, not proof of why they recommended anything.

docs.github.com210
dev.to150
github.com147
cursor.com122
arxiv.org88
daily.dev72
zapier.com72
help.openai.com62
pecollective.com55
augmentcode.com51