GEO Benchmark — AI Search Visibility 📈

foXLabs AI-visibility series: GEO auditor · AI brand monitor

🎉 Benchmark a brand’s visibility in AI answers — no login, no API key, one row per query/brand, with mention rate, citations and competitor share. Built for SEO/GEO, marketing and brand teams.

🔍 What is the GEO Benchmark — and when should you use it?

Give this actor brands, domains or prompts and it returns matching brands from live AI-assistant answers (generative-engine visibility) — as clean, deduplicated rows you can filter, export or feed to an AI agent. Every run reads the source live.

Use it when you need: how often a brand appears in AI answers; competitor share of voice; or a GEO visibility benchmark.

Use something else when: you need classic SEO rankings — this measures AI-answer visibility, not search-engine positions.

🤖 Use with AI agents

Already on the Apify MCP server? Ask for this Actor by name: foxlabs/geo-benchmark.

Your agent can pay for its own runs. This Actor is pay-per-event with agentic payments, so an agent can discover it, run it and settle the bill over x402 (USDC on Base) or Skyfire — no Apify account or API token of its own. Billing is the same either way: per delivered record, never for errors.

Otherwise paste this into Claude, ChatGPT, Cursor or any MCP-enabled assistant:

I want to pull brand company records using the Apify Actor `foxlabs/geo-benchmark`.
Input: `yourSite`, `competitors`, `maxPagesPerSite` — see the Input table below. 
Start with: {"yourSite":"https://www.notion.so","competitors":["https://coda.io","https://www.clickup.com"]}
Ask me what to look up, run the Actor, then summarise the rows as a table.

The machine-readable API, MCP config and OpenAPI definition live at apify.com/foxlabs/geo-benchmark.md.

📋 Overview

Everything you need to turn live AI-assistant answers (generative-engine visibility) into clean, structured data — in one actor, with no login, cookies or API key.

Why teams pick this actor:

• ✅ Whole analysis, one call — name or ID in, matching brands out.
• 🧹 No empty-promise columns — only fields this registry actually fills; degenerate columns are removed.
• 🔗 Stable identifiers — every row carries the source's own IDs, ready to join across runs and to other Fox Labs actors.
• 💰 Per-row pricing — a minimal price per delivered row, no subscription.
• 🤖 Agent-ready — MCP + x402 agentic payments.

✨ Features

• 🔍 Name or ID lookup — relevance-ranked name search or exact registry-ID lookup.
• 🏢 Full entity profile — status, legal form, formation date, address and the registry’s own contact fields.
• 🧹 Clean schema — deduplicated camelCase rows, ready for CSV/Excel/JSON.

🎬 Quick Start

curl -X POST "https://api.apify.com/v2/acts/foxlabs~geo-benchmark/runs?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"yourSite":"https://www.notion.so","competitors":["https://coda.io","https://www.clickup.com"]}'

🚀 Getting Started (3 steps)

1. Choose your targets — brands, domains or prompts.
2. Review the options — every field is optional unless marked required.
3. Run and export — get a clean dataset as JSON, CSV or Excel.

📥 Input

{"yourSite":"https://www.notion.so","competitors":["https://coda.io","https://www.clickup.com"]}

Field	Type	Description
yourSite	string	The website you want to benchmark (e.g. "https://www.yourbrand.com"). It is ranked against the competitors below on AI-search readiness.
competitors	array	1–5 competitor websites to benchmark against your site. Each is audited the same way and ranked side-by-side.
maxPagesPerSite	integer	How many internal pages to crawl & score per site (starting from each site's URL). Keep low for a fast, cheap benchmark; raise for a fuller picture.
proxyConfiguration	object	Leave OFF for fast, free audits — most sites work directly (we already auto-retry the www↔non-www variant). Turn on Apify Proxy with the RESIDENTIAL group ONLY…

📤 Output

One row per result, saved to the dataset. Every row carries scrapedAt. Lookups that cannot be completed are reported in the run log rather than silently dropped.

Field	Description
type	Type
domain	Domain
isYou	Is You
rank	Rank
overallGeoScore	Overall Geo Score
band	Band
pagesAudited	Pages Audited
accessScore	Access Score
structuredScore	Structured Score
extractabilityScore	Extractability Score
speedScore	Speed Score
trustScore	Trust Score
aiAccessText	Ai Access Text
blockedAiBotsText	Blocked Ai Bots Text
schemaTypesText	Schema Types Text
jsRenderedPages	Js Rendered Pages
hasLlmsTxt	Has Llms Txt
yourDomain	Your Domain
yourRank	Your Rank
totalSites	Total Sites
yourScore	Your Score
leaderDomain	Leader Domain
leaderScore	Leader Score
scoreGapToLeader	Score Gap To Leader
scoreboardText	Scoreboard Text
dimensionGapsText	Dimension Gaps Text
botGapsText	Bot Gaps Text
schemaGapsText	Schema Gaps Text
winsText	Wins Text
prioritizedMovesText	Prioritized Moves Text
generatedAtIso	Generated At Iso

💼 Use cases

1. GEO benchmarking — measure a brand’s AI-answer visibility. Input: brands or prompts. Output: mention rate + citations. Use: a GEO scorecard.

2. Competitor share — compare share of voice vs rivals. Input: brand + competitors. Output: share of voice. Use: a positioning view.

3. Content gaps — find prompts where a brand is absent. Input: prompts. Output: presence per prompt. Use: a content plan.

🔗 Integration

JavaScript / Node.js

import { ApifyClient } from 'apify-client';
const client = new ApifyClient({ token: 'YOUR_TOKEN' });
const run = await client.actor('foxlabs/geo-benchmark').call({"yourSite":"https://www.notion.so","competitors":["https://coda.io","https://www.clickup.com"]});
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items[0]);

Python

from apify_client import ApifyClient
client = ApifyClient('YOUR_TOKEN')
run = client.actor('foxlabs/geo-benchmark').call(run_input={"yourSite":"https://www.notion.so","competitors":["https://coda.io","https://www.clickup.com"]})
for item in client.dataset(run['defaultDatasetId']).iterate_items():
    print(item)

Automation (n8n / Zapier / Make): schedule or webhook → HTTP request to the actor API with your input → handle the JSON dataset → push to a sheet, CRM or dashboard.

📊 Pricing

Pay-per-event: per delivered record. Empty or failed lookups are never billed. View current pricing.

❓ FAQ

Do I need an account, login or API key? No. This reads live AI-assistant answers (generative-engine visibility).

What do I search by? Brands, domains or prompts.

How current is the data? Every run queries the source live, so results are as fresh as the registry.

What does it measure? Brand mention rate, citations and competitor share of voice across AI-assistant answers.

Can I export to CSV / Excel / JSON? Yes — directly from the Apify dataset.

🐛 Troubleshooting

• Fewer rows than expected — raise the result cap, or refine the input.
• A name returns an unexpected entity — it matched a similar registered name; search the exact registry ID.
• No rows for a name — try the entity’s exact legal name or its registry ID.

⚖️ Is it legal to scrape this data?

This actor queries public AI assistants and analyses their answers for brand visibility. Results can still contain personal data (e.g. a person’s name); personal data is protected by the GDPR and similar laws, so only process it with a legitimate basis. See Apify’s blog post on the legality of web scraping.

🤝 Support & contact

• 🌐 Website: data.foxlabs.com.tr
• 📧 Email: info@foxlabs.com.tr
• 🐛 Issues: open a ticket in the Actor’s Issues tab
• 🧰 More clean B2B data actors: Fox Labs on Apify

Changelog

0.1.18 — 2026-09-20 — README examples corrected against the real input schema

• The README's code examples did not match this Actor. They used queries and maxResultsPerQuery — keys that do not exist in this Actor's input schema — with a placeholder value, and the input table listed those same phantom fields. Anyone who copied the AI-agent, cURL, JavaScript or Python example got a failing run. Every example now uses the real schema and matches the Console prefill: {"yourSite":"https://www.notion.so","competitors":["https://coda.io","https://www.clickup.com"]}
• The input table is regenerated from input_schema.json, so it lists the fields the Actor actually accepts.
• Removed claims carried over from the same generator template where present: "formation / status monitoring", "a canonical registry record for KYB and due diligence", "every row carries query", and industry described as a NACE code.
• No code, output field or pricing change.

0.1 — 2026-09-07

• Enabled AI-agent payments (x402) + rebuilt the README to the full standard (What-is / when, AI-agents + x402 agentic payments + MCP, Overview, Features, Use cases, Integration, FAQ, Troubleshooting, Support & contact).

0.0

• Initial release: data from live AI-assistant answers (generative-engine visibility) by name or registry ID.