Hanzo
OpenapiEval

Is your past runs and how they scored — the dataset and model, the judge model,…

Is your past runs and how they scored — the dataset and model, the judge model, how many examples were attempted and how many scored, the average score,…

GET /v1/eval/runs

Addresshttps://api.hanzo.ai/v1/eval/runs
MethodGET
Operationget_eval_runs
AuthAuthorization: Bearer $HANZO_API_KEY

Is your past runs and how they scored — the dataset and model, the judge model, how many examples were attempted and how many scored, the average score, and when it happened.

Requires a validated principal; 403 without one, and rows are filtered on the validated org. These records come from the metastore rather than the datastore, so they are readable on a deployment with no telemetry wired — but a run's traces and scores are not.

Request

2 fields.

FieldInTypeRequiredDescription
datasetNamequerystringDataset narrows to the runs against one dataset.
limitqueryinteger

Response

StatusBodyMeaning
200runsok

200 body — 10 fields.

FieldInTypeAlwaysDescription
databodyrunRecord[]Data is the caller org's runs, bounded by limit.
data[].avgScorebodynumberAvgScore is the mean over the scored examples.
data[].createdAtbodystringCreatedAt is when the run first landed.
data[].datasetbodystringDataset is the set that was scored.
data[].itemsbodyintegerItems is how many examples were attempted.
data[].judgeModelbodystringJudgeModel is the model that graded.
data[].modelbodystringModel is the model under test.
data[].runNamebodystringRunName is the run's label.
data[].scoredbodyintegerScored is how many produced a real score.
data[].updatedAtbodystringUpdatedAt is when the record last changed.

Failure carries the platform error shape — see Errors.

Examples

hanzo evals runs get

Eval API · All Hanzo APIs · Interactive reference

How is this guide?

On this page