---
title: "Judge Complementarity"
method: GET
path: "/api/v1/judges/complementarity/{ranking_id}"
tags: ["LLM Judges"]
---

# Judge Complementarity

`GET /api/v1/judges/complementarity/{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/complementarity/{ranking_id}`
- Auth: none declared

Does the human + judge TEAM beat either of them alone?

The sibling `/agreement` and `/disagreements` endpoints measure
substitution: how closely the judge reproduces the human. Both peak when
the judge is a perfect replica — which is worth nothing to a team, because
a replica never rescues a pair the human got wrong.

This endpoint measures the other axis. It scores a single held-out rater
and the judge against the *same* leave-one-out consensus of the remaining
raters, splits the outcomes into a 2x2 (the off-diagonals are where
complementarity lives), and sweeps a deferral threshold — the machine
answers when its confidence clears τ, a human answers otherwise — to find
what the pair achieves together.

With no `judge_id` the ranking's most prolific judge is used and named in
the response. A hardcoded default would report "insufficient" on a ranking
judged by anything else, which reads as thin data rather than as a wrong
argument.

Reads persisted votes only: no judge calls, so nothing is metered.

## Path parameters

- `ranking_id` string, required

## Query parameters

- `judge_id` string, nullable
- `declared_tau` number, nullable
- `seed` integer

## Response `200`

Successful Response

- unknown

## Other responses

- `422`: Validation Error

---

[API](https://skmtc.dev/aimrank/apis/aimrank-api.md) · [All operations](https://skmtc.dev/aimrank/apis/aimrank-api/llms.txt) · [OpenAPI document](https://skmtc.dev/aimrank/apis/aimrank-api/revisions/3574d0aff459?raw)