For AI agents: a documentation index is available at /llms.txt. Append .md to any page URL for markdown, or send Accept: text/markdown.
List Prompt Version Eval Run Results
List the per-row results of an offline evaluation job: one record per dataset row and grader, with the graded output, score, groups and the trace it came fro…
List the per-row results of an offline evaluation job: one record per dataset row and grader, with the graded output, score, groups and the trace it came from when known.
https://statsigapi.net/console/v1/prompts/{id}/versions/{versionId}/eval_runs/{runId}/resultsAuthorizations
STATSIG-API-KEYstringrequiredapiKey (header)
Path parameters
idstringrequiredPrompt id or name
versionIdstringrequiredPrompt version ID
runIdstringrequiredEval run ID
Query parameters
limitintegerResults per page
10stringnumberpageintegerPage number
1stringnumberResponse
application/jsonmessagestringrequiredA simple string explaining the result of the operation.
dataobject[]requiredShow child attributes
rowIDstringrequiredDataset row the result belongs to. Rows sent through send_results are numbered from 0.
graderIDstringrequiredscorenumberrequiredformat: doublecolumnsobject[]requirednamestringrequiredvaluestringrequiredoutputstringrequiredCompletion that was graded.
judgeResponsestringrequiredgroupsstring[]requiredtraceIDstringrequirednullablespanIDstringrequirednullablerunTimenumberrequiredformat: doublepaginationobjectrequiredPagination metadata for checking if there is next page for example.
Show child attributes
itemsPerPagenumberrequiredformat: doublepageNumbernumberrequiredformat: doublenextPagestringrequirednullablepreviousPagestringrequirednullabletotalItemsnumberformat: doubleallstringstatusintegerrequired404messagestringrequiredWas this helpful?