Agency · Evaluation
Pentagram
Compliance Index score
48.3/100 · F
= flat since last week
Per-category breakdown
Each category is scored independently. The cohort average shows how this site compares to the 30-site cohort in each dimension.
Evaluation
Pentagram scores 48.3/F on the Designesy Compliance Index — 10 of 42 checks passed, 3 failed, 12 warned, 14 skipped. The cohort mean is 69.3/D across 30 scored sites. Pentagram sits 30% below the cohort mean.
Strongest category: Poise at 75.0%. Weakest scored category: Interaction at 0.0%. The gap between best and worst is the finding — most systems are strong in one dimension and absent in another.
The engine detected 181 custom properties at :root — a rich token layer. The question is whether those tokens are structured (primitive → semantic → component) or flat.
F-grade means Pentagram scores below 60 — the contract's pass threshold. The failing checks are not subjective: they are missing CSS primitives that the contract requires at :root.
This evaluation is deterministic — no LLM, no human judgment, no survey. The same 42-check engine that scored Pentagram scores every site on the leaderboard. Re-score pentagram.com live to see if anything has changed since 2026-08-03.
Scored 2026-08-03 against contract v0.4.0 (42 checks, 14 weighted categories). Re-scored weekly via GitHub Action.
Cohort context
This site
48.3/100
Cohort mean
69.3/100
Cohort median
70.0/100
Delta from mean
-21.0
Why this site is scored
Parent-system posture analog