PSYCHOMETRICS · BUT MOSTLY VIBES

Measures that barely work.

Rigorous-looking scores for texts that have no business being on a scale. Backed by a language model and one CSV of 30 passages someone scored on a Tuesday.

Inspired by industry leaders whose own scale also doesn't work.

Honest comparison

How we stack up against the incumbent.

Industry leader

MetaMetrics® Lexile®

"Measures That Inspire"

  • Decades of psychometric research
  • Trademark with a registered ®
  • May or may not correlate with cognitive load
  • Can be used as a random number generator
  • Closed methodology; trust us bro
Our offering

me-go · ضاد

"Measures That Barely Work"

  • Returns a number between 100 and 1600
  • Shows you exactly why it picked that number
  • Honest about being mostly an LLM with a CSV
  • Reproducibility: aspirational
  • Validation study: forthcoming, possibly
Methodology

The science is mostly the prompt.

1

30 anchors

A small CSV of passages with human-assigned difficulty scores. Small enough to fit in a chat, big enough to publish a paper.

2

Pairwise judgment

GPT-4.1 reads your text against each anchor and decides which is harder. Thirty calls in parallel. Costs roughly a coffee.

3

Logistic fit

We fit a logistic curve through the pairwise results, scale the estimate to 100–1600, and present it with appropriate gravitas.