LLM Judges

Judge Eval History

Recent scheduled eval-regression runs for a ranking.

Each row is one recorded LLM-vs-human alignment snapshot (Cohen κ + agreement_pct + overlap + regression flag vs. the prior run). The daily ARQ cron (run_eval_regression) appends these; this endpoint surfaces the longitudinal trend for the JudgeAlignmentPanel.

get/api/v1/judges/eval-history/{ranking_id}

Request

  • Base URL: https://app.aimrank.io (the document declares no server; this is the origin it was published from)
  • URL: https://app.aimrank.io/api/v1/judges/eval-history/{ranking_id}
  • Auth: none declared

Path parameters

ranking_idstring required

Query parameters

limitinteger

Response

Successful Response

unknown required

Changes

No recorded changes to this operation across all 1 revision of this API.