geo-score
Will ChatGPT cite your site? Score it in 20 seconds.
curl -sL https://raw.githubusercontent.com/jianruntech/geo-score/main/cli/geo_score.py \
| python3 - stripe.com --brief
One command. About twenty seconds. Every check, and what the next tier needs.
AIV READINESS https://stripe.com
──────────────────────────────────────────────────────────────────────────
71 / 100 Solid
12 points to Leading
Reachable 11/15
◐ Crawlers allowed in robots.txt ███████████░░░░░░░ 3/5
✓ Reachable to retrieval agents ██████████████████ 5/5
◐ Main content server-rendered ███████████░░░░░░░ 3/5
Understandable 15/22
◐ Sitemap discoverable and fresh █████████░░░░░░░░░ 2/4
✓ llms.txt present and structured ██████████████████ 5/5
✓ Organization + WebSite schema ██████████████████ 6/6
✗ BreadcrumbList on nested pages ░░░░░░░░░░░░░░░░░░ 0/3
◐ Page-type schema (Product, FAQ…) █████████░░░░░░░░░ 2/4
Content Citability 25/35
✓ Self-contained answer passages ██████████████████ 9/9
◐ Headings match how people ask ████████░░░░░░░░░░ 3/7
◐ Freshness signal present █████████░░░░░░░░░ 3/6
✓ Statistics carry a source ██████████████████ 7/7
◐ Named, verifiable authorship █████████░░░░░░░░░ 3/6
Brand Credibility 8/10
⊘ Third-party listings ·················· —
⊘ Independent mentions ·················· —
✓ Knowledge-graph entity ██████████████████ 4/4
◐ sameAs links resolve ████████████░░░░░░ 2/3
◐ Video and multimodal presence ████████████░░░░░░ 2/3
Answer Fit 2/4
◐ Content shaped for extraction █████████░░░░░░░░░ 2/4
⊘ Covers the questions people ask ·················· —
⊘ Chinese engine readiness ·················· —
Biggest gaps
+4 Headings match how people ask about half do
+3 Named, verifiable authorship and the name links to a verifiable identity page
+3 Freshness signal present most pages do, and dateModified agrees with the visible date
Scored 61 / 86 observable · 4 checks left the denominator · rubric v1.1
Needs judgement: p3.listings, p3.mentions, p4.question-coverage, p4.cn-engines
Full rubric and what each tier means:
https://github.com/jianruntech/geo-score
Python 3.8+, standard library only, nothing to install. It reads public URLs and prints a score against a published, versioned rubric — not a black box.
See how 314 well-known sites score → · a quarter of them cannot be cited at all.
GEO means Generative Engine Optimization — getting cited by ChatGPT, Perplexity, Google AI Overviews, Gemini and Copilot. Nothing to do with geography or maps.
Why this is a different question from SEO
Classic SEO asks where do I rank. Answer engines don't rank — they retrieve passages, decide whether a source is worth quoting, and cite it. Different question, different failure modes: a site can sit at position 3 on Google and never be quoted, while a page nobody links to gets cited daily because its passages are clean.
Most of what determines this is mechanical and cheap to fix — a robots.txt line, a
JSON-LD block, a date in a template, a paragraph rewritten so it stands on its own. The
hard part is knowing which of them you are missing, and what each one is worth.
What it checks
21 tiered checks totalling 100 points, plus 4 bonus checks worth up to +6 outside the denominator. Full specification: rubric/v1.1.md · 简体中文
| Pillar | Pts | Asks |
|---|---|---|
| Reachable — gates | 15 | Can a retrieval crawler get the page at all? robots.txt, live reachability across 10 AI user-agents, server-rendered content |
| Understandable | 22 | Can it tell what the page and the company are? Organization + WebSite, llms.txt, sitemap, breadcrumbs, page-type schema |
| Content Citability | 35 | Is there anything here worth quoting? Self-contained answer passages, headings that match how people ask, sourced figures, real bylines, freshness |
| Brand Credibility | 18 | Why should an engine trust it? Knowledge-graph entity, third-party listings, sameAs that resolves, video presence |
| Answer Fit | 10 | Is the content shaped to be lifted into an answer? |
Content Citability carries the most weight on purpose: answer engines retrieve passages, not domains. Passage shape beats domain authority more often than classic SEO intuition expects.
Every scored check is tiered — 2 to 4 tiers, each naming a count out of the 8 sampled pages, so two people scoring the same site agree on the arithmetic. Three checks are gates: score zero on crawler access, live reachability or server-rendered content and the result caps at 40, because until a crawler can reach the content nothing else you change has any effect.
Bands
| 0–30 | 31–50 | 51–65 | 66–82 | 83–100 |
|---|---|---|---|---|
| Not started | Early | Growing | Solid | Leading |
Band names describe a stage, not a verdict. External benchmarks put most business sites in the 30–55 range, so a score in the forties is ordinary, not alarming.
314 sites, scored in public
A quarter of them cannot be cited at all. 80 sites have a gate check at zero — a
retrieval crawler simply cannot get the content. 19 block AI crawlers by name in
robots.txt, which is an editorial choice and reported as such — amazon.com lands at 12
for exactly this reason. 45 serve a page whose body only exists after JavaScript runs.
Their content is there, a browser sees it, and a crawler gets an empty shell. That group
almost certainly did not choose it. A further 16 hand a crawler an outright error.
Median 56. Range 12 to 98.
| Site | Score | Band |
|---|---|---|
| pulumi.com | 98 | Leading |
| minimaxi.com | 95 | Leading |
| lumalabs.ai | 93 | Leading |
| resend.com | 93 | Leading |
| ironcladapp.com | 91 | Leading |
| … | ||
| amazon.com | 12 | Not started |
| keepa.com | 12 | Not started |
| mercadolibre.com | 12 | Not started |
The full table, by sector → · markdown · raw data · re-run it
Two more findings worth the click: sites built for the Chinese market score 19 points lower than everyone else (median 40 against 59 — a gap that has held between 16 and 23 points across five separate samples, from 38 sites up to 314), and the same three cheap things — a date in the page template, an opening paragraph that stands on its own, one JSON-LD block — are missing from more than half the field.
Every number here is reproducible with the command at the top of this page — and we measured how reproducible. Running the whole benchmark twice and comparing every site: 96% land within ±5, 45% land identically. Read one site's score as ±5 rather than as exact; medians are stable. The unstable part is the gate checks, where five sites flipped between runs because their bot protection answered a crawler differently. The band, the control experiment and the per-site pairs are in benchmark/REPRODUCIBILITY.md.
For five reference sites we also publish hand-scored audits covering all 21 checks, with the evidence behind each one: examples/audits/v1.1/.
Three ways to run it
CLI — no install, no dependencies, 20 seconds.
python3 cli/geo_score.py example.com # human-readable
python3 cli/geo_score.py example.com --explain # with the evidence behind every check
python3 cli/geo_score.py example.com --json # conforms to schema/report.v2.json
python3 cli/geo_score.py example.com --compare competitor.com # side by side
python3 cli/geo_score.py example.com --badge aiv-badge.svg # embeddable SVG
python3 cli/geo_score.py example.com --share # one line to paste somewhere
GitHub Action — score on every push, fail the build when it regresses.
- uses: jianruntech/geo-score@v1
with:
url: https://example.com
fail-under: 40
Claude Code skill — the CLI measures what a static fetch can see. Four checks need off-site search or human judgement, and the skill does those too.
git clone https://github.com/jianruntech/geo-score ~/.claude/skills/geo-score
# then: /geo-score audit https://example.com
The CLI leaves those four checks out of the denominator rather than guessing, so it reads a little lower than a full audit — typically by 5 to 15 points on an established brand, which has listings and mentions the CLI cannot see.
Why a rubric, not just a tool
A score you cannot audit is a number someone made up. So the specification is the product, and the tools are implementations of it:
- **Vers