Outputs

Once you’ve configured your evaluator, you can start evaluating text inputs for grade level appropriateness:

example.ts

const evaluator = new GradeLevelAppropriatenessEvaluator(configOptions);

const text = "The cat's out of the bag now.";

await evaluator.evaluate(text);

Literacy evaluator family

The Text Complexity Evaluator runs multiple literacy evaluators on the provided text input:

The output:

Throws an error if all literacy evaluators fail
Otherwise outputs an error or result for each literacy evaluator

For other evaluators

All literacy evaluators besides the parent Text Complexity Evaluator have the following output fields.

Field	Type	Description
`score`	`TextComplexityLevel` ↗	Complexity classification returned by the evaluator. Purpose evaluator also accepts “More context needed” for cases where the text alone is insufficient to determine complexity.
`reasoning`	`string`	Explanation for the assigned complexity score
`metadata`	`EvaluationMetadata` ↗	Includes model used to generate the evaluation, total evaluation processing time in milliseconds, input tokens, and output tokens.
`_internal`	Unique to each evaluator	Detailed internal analysis data specific to each evaluator.

The _internal field includes detailed internal analysis data specific to that evaluator:

Evaluator	`_internal` description	`_internal` type
Grade Level Appropriateness	Output fields	`GradeLevelAppropriatenessInternal` ↗
Subject Matter Knowledge v0.2.0	Output fields	`SmkInternal` ↗
Vocabulary	Output fields	`VocabularyInternal` ↗
Sentence Structure	Output fields	`SentenceStructureInternal` ↗
Conventionality v0.3.0	Output fields	`ConventionalityInternal` ↗
Purpose v0.5.0	Output fields	`PurposeInternal` ↗

Understanding evaluators

Getting started

SDK API Reference

Literacy evaluators

Feedback evaluators

Standards evaluators

Datasets

Resources

Literacy evaluator family

For other evaluators

​Literacy evaluator family

​For other evaluators

Literacy evaluator family

For other evaluators