Data & Analytics

The load-bearing vocabulary of Claude

Last updated 2026-08-27 · benchmark measured 2026-08-27 — deterministic & reproducible

A tool tracking the spread of AI-generated vocabulary in GitHub pull requests.

Is The load-bearing vocabulary of Claude production-ready?

Legit.Show scores The load-bearing vocabulary of Claude 66 out of 100 — the simple average of its 7 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on The load-bearing vocabulary of Claude (public-surface assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Performance; its weakest is Security. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

• Performance — 100/100
• Accessibility — 87/100
• Security — 10/100
• Privacy — 25/100
• Reliability — 100/100
• Standards — 92/100
• Discoverability — 47/100

What we measured

• No Content-Security-Policy and no HSTS.
• Served over HTTPS with a valid certificate.
• Real Lighthouse performance run — 41 ms to first byte.
• Returns a proper 404 for unknown routes.
• 3 of 3 sampled routes reachable.
• No privacy policy found.
• Sets cookies / loads scripts with no consent prompt.

Who it's for

ML researchers · Data analysts · AI developers · GitHub ecosystem researchers · NLP practitioners

Visit The load-bearing vocabulary of Claude → · Alternatives to The load-bearing vocabulary of Claude → · How this was measured →