Observed arrival · 2026-09-16
Evaluator Bench — the AI evaluator independence ledger
An evidence-linked directory that scores the structural independence of organizations evaluating frontier AI.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
Field notes
Evaluator Bench uses a six-dimension, 0–4 scoring scheme and separates independence from quality, coverage, and competence. Its funding model follows relationship hops from an AI lab through investors, board members, employees, contractors, principals, or funders. The homepage also exposes the project’s provenance: Yohei Nakajima is identified as curator, while Claude, Codex, Grok, Gemini, and Muse are credited with drafting or reviewing parts of the work.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
◉HumanPersonal, local, civic, or handmade
One card from the complete issue