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 34% 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 2026-09-28. Below is how often each brand came up, and how often it was the first one recommended.

Leader

Cursor

First pick in 34% of answers

Answers read

450

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 4 points on first picks (34% to 30%). At this sample size that is too close to call: treat them as level.
  • GitHub Copilot comes up in 75% of answers but is named first in 21%: the widest gap in the top eight between being mentioned and being the first pick.
Published 2026-10-28Method v4Each question asked 5× per assistant6 assistants: ChatGPT · Claude · Claude Code (local) · Codex (local) · Gemini · Perplexity
Measured 2026-09-28An older reading · see the latest boardUpdates 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
01Cursor370/45034%
02Claude Code317/45030%
03GitHub Copilot339/45021%
04CodeRabbit29/4504%
05Replit Agent40/4502%
07Greptile22/4502%
08Devin17/4502%
09Windsurf94/4501%
11Codex199/4501%
12Aider44/4501%
13Augment20/4500%
14Cline42/4500%
15JetBrains AI28/4500%
17Amazon Q22/4500%
18Continue21/4500%
19Qodo19/4500%
20OpenCode18/4500%
21Bolt.new17/4500%
22Lovable16/4500%
23Tabnine16/4500%
24Zed14/4500%
25OpenHands3/4500%
26Roo Code3/4500%

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

Each assistant’s favourite

Taken one at a time, the 6 assistants split between 2 favourites: Claude Code and Cursor.

ChatGPTClaude Codefirst in 25 of 75 answers
ClaudeClaude Codefirst in 24 of 75 answers
Claude Code (local)Claude Codefirst in 38 of 75 answers
Codex (local)Cursorfirst in 32 of 75 answers
GeminiCursorfirst in 38 of 75 answers
PerplexityCursorfirst in 25 of 75 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 OWN86%129/150RIVALS63%188/300+23.3
Codexmade by the company behind ChatGPT and Codex (local)ITS OWN47%70/150RIVALS43%129/300+3.7
Google Antigravitymade by the company behind GeminiITS OWN0%0/75RIVALS3%10/375-2.7
Gemini Code Assistmade by the company behind GeminiITS OWN7%5/75RIVALS18%68/375-11.5

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.

github.com168
dev.to164
daily.dev150
augmentcode.com126
nxcode.io107
cursor.com94
docs.github.com94
zapier.com82
verdent.ai72
axify.io71