Skip to main content
Evaluator last updated May 7, 2026.

Overview

The Purpose evaluator assesses how clearly a text communicates its central purpose – whether it is to inform, persuade, explain, describe, or entertain. The evaluator analyzes whether a text’s intent is explicitly stated, indirectly hinted at, or masked (e.g., text may present as neutral information, but be building a persuasive argument).

At a glance

The evaluator was built and validated using the model and temperature below (other configurations will produce different results and may have lower accuracy):

Getting started

Follow the Quickstart to start using this evaluator:

Inputs

Output

Interpreting results

High or low complexity scores are not inherently good or bad. A higher complexity score simply indicates a text that requires more interpretation by readers.
Example: A “Very complex” or “Exceedingly complex” text may be ideal if the instructional goal is identifying implicit or persuasive intent. However, that same text may not be a good fit if the instructional goal is content comprehension.

Accuracy and validation

This evaluator is provided as Early access. Comprehensive accuracy measures are still evolving, and validation testing is ongoing.
The evaluator was optimized using 35 annotated passages from the CLEAR Corpus ↗ and validated through expert review of additional samples.
Exceedingly complex texts aren’t common in lower grades and the benchmark dataset doesn’t include many examples of them. Use caution when applying this evaluator to higher grade levels where such texts are more frequent.

Evaluator release history