Get a run's rubric scorecard

The deterministic rubric result for one run. No model, no spend.

Divide by sessionsGraded, never sessionsTotal, and keep failedGradingCount separate from failCount — a crashed judge is not a regression.

get/projects/{projectId}/goal-runs/{runId}/scorecard

Response

The scorecard.

runIdstring required

sessionsTotalinteger required

sessionsGradedinteger required

The DENOMINATOR for any rate you compute. Never divide by sessionsTotal — 3 failures of 4 graded sessions out of 40 attempted is not 7.5%.

Changed in 1 of the 122 revisions of this API.1

Sep 22, 2026561e4fd0dfa21See the full diff
- ○
  endpoint added
  endpoint-added
This revision also has 50 changes that name no endpoint, such as unreferenced schemas being removed. See the revision's changelog