Skip to content

List evaluation results

GET
/evaluations/{evaluationId}/results

List all evaluation results for a specific evaluation. Results are created as the evaluation runs and track per-example outcomes.

evaluationId
required

ID of the parent evaluation to list results for

string

ID of the parent evaluation to list results for

evaluationResultIds

Comma-separated list of result IDs to filter by

string
nullable

Comma-separated list of result IDs to filter by

statuses

Comma-separated list of statuses to filter by (pending, passed, failed, error, skipped)

string
nullable

Comma-separated list of statuses to filter by (pending, passed, failed, error, skipped)

page

Page number for pagination (1-indexed)

number
>= 1

Page number for pagination (1-indexed)

pageSize

Number of results per page (1-100, default: 20)

number
>= 1 <= 100

Number of results per page (1-100, default: 20)

orderBy

Field to sort results by

string
Allowed values: createdAt completedAt status score

Field to sort results by

orderDirection

Sort direction: ascending or descending

string
Allowed values: asc desc

Sort direction: ascending or descending

Evaluation results retrieved successfully

object
evaluationResults
required

Array of evaluation results matching the query

Array<object>
object
evaluationResultId
required

Unique identifier for the evaluation result (nanoid format)

string
evaluationId
required

ID of the parent evaluation

string
exampleId
required

ID of the example being evaluated

string
executionId
required

ID of the pipeline execution created for this example

string
nullable
status
required

Status: ‘pending’, ‘passed’, ‘failed’, ‘error’, or ‘skipped’

string
Allowed values: pending passed failed error skipped
mappedInput

Example input mapped to pipeline input format

nullable
actualOutput

Output from pipeline execution

nullable
score
required

Evaluation score (0.0 to 1.0)

number
nullable
feedback
required

Evaluator explanation/feedback

string
nullable
errorMessage
required

Error details if status is ‘error’ or ‘skipped’

string
nullable
startedAt
required

When processing started for this example (ISO 8601)

string format: date-time
nullable
completedAt
required

When processing completed for this example (ISO 8601)

string format: date-time
nullable
createdAt
required

When the result was created (ISO 8601)

string format: date-time
total
required

Total number of evaluation results matching the query (before pagination)

number
page
required

Current page number

number
pageSize
required

Number of results per page

number

Bad Request - Validation error or invalid input

object
error
required
string
code
string
details
nullable
retryable
boolean

Unauthorized - Authentication required or invalid token

object
error
required
string
code
string
details
nullable
retryable
boolean

Forbidden - Insufficient permissions

object
error
required
string
code
string
details
nullable
retryable
boolean

Not Found - Resource does not exist

object
error
required
string
code
string
details
nullable
retryable
boolean