---
title: "Returns a page of the requested confidence zone of an A-vs-B matchup — the prompts A clearly
 wins, the coin flips, or the prompts B clearly wins."
method: GET
path: "/benchmark/{benchmarkId}/matchup-breakdown"
tags: ["Benchmark"]
---

# Returns a page of the requested confidence zone of an A-vs-B matchup — the prompts A clearly
 wins, the coin flips, or the prompts B clearly wins.

`GET /benchmark/{benchmarkId}/matchup-breakdown`

Each vote is weighted by the annotator's reliability; a prompt is placed by the Wilson score
 interval on A's win share and, within the requested zone, ordered most-confident first (coin
 flips by effective sample size). The same vote-level filters as the matrix query apply.
 Benchmarks without granular votes return an empty page.

## Path parameters

- `benchmarkId` string, required

## Query parameters

- `participantA` string, required
- `participantB` string, required
- `zone` unknown
- `page` integer
- `page_size` integer
- `country` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `language` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `gender` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `age_bucket` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `occupation` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `tags` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `participant_id` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `leaderboard_id` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `run_id` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `prompt_identifier` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `voted_at` object
  - `eq` string
  - `neq` string
  - `gt` string
  - `gte` string
  - `lt` string
  - `lte` string
  - `contains` string
  - `starts_with` string
  - `ends_with` string
  - `in` string[]
  - `not_contains` string
- `logic` 'and' | 'or'

## Response `200`

OK

- GetBenchmarkMatchupBreakdownEndpointPagedResultOfOutput
  - `total` integer, required
  - `page` integer, required
  - `pageSize` integer, required
  - `items` GetBenchmarkMatchupBreakdownEndpointOutput[], required
    - `promptId` string, nullable — The prompt entity id, or null when the identifier has no live prompt.
    - `promptIdentifier` string, required — The stable identifier of the prompt within the benchmark.
    - `englishPrompt` string, nullable — The prompt text translated to English, if any.
    - `originalPrompt` string, nullable — The prompt text as originally provided, if any.
    - `promptAsset` union
      - object
        - `_t` 'FileAsset', required
        - `fileName` string, required
        - `metadata` MetadataModelCollection, required
        - `identifier` string, required
      - object
        - `_t` 'MultiAsset', required
        - `assets` IAsset[], required
        - `metadata` MetadataModelCollection, required
        - `identifier` string, required
      - object
        - `_t` 'NullAsset', required
        - `metadata` MetadataModelCollection, required
        - `identifier` string, required
      - object
        - `_t` 'TextAsset', required
        - `text` string, required
        - `metadata` MetadataModelCollection, required
        - `identifier` string, required
    - `rawWinsA` integer, required — The number of votes A won on this prompt.
    - `rawWinsB` integer, required — The number of votes B won on this prompt.
    - `weightedWinsA` number, double, required — The reliability-weighted wins for A (summed annotator userScore).
    - `weightedWinsB` number, double, required — The reliability-weighted wins for B (summed annotator userScore).
    - `effectiveN` number, double, required — The reliability-weighted sample size, WeightedWinsA + WeightedWinsB.
    - `wilsonCenter` number, double, required — The Wilson score interval center for A's win share.
  - `totalPages` integer

## Other responses

- `400` — Bad Request
- `401` — Unauthenticated
- `403` — Forbidden

---

[API](https://skmtc.net/rapidata/apis/rapidata-api.md) · [All operations](https://skmtc.net/rapidata/apis/rapidata-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/rapidata/rapidata-api/revisions/e42ec51c7b88/schema)