---
title: "Queries the per-image ratings of a benchmark — a page of prompts, each with its ranked images
 and the pairwise win matrix over them, in the same pandas-split shape as the standings matrix."
method: GET
path: "/benchmark/{benchmarkId}/images/query"
tags: ["Benchmark"]
---

# Queries the per-image ratings of a benchmark — a page of prompts, each with its ranked images
 and the pairwise win matrix over them, in the same pandas-split shape as the standings matrix.

`GET /benchmark/{benchmarkId}/images/query`

Filters apply to the underlying votes and use the same field set as the standings query.
 Ordering (extremeness by default) selects which prompts a page fits; a rating is an image's
 standing against all images on its prompt, so a participant filter narrows the rows but does not
 refit. Matrix axes are the image labels — a participant's name, suffixed -{n} when it has
 several images on the prompt. A prompt with no matching votes yields no rows.

## Path parameters

- `benchmarkId` string, required

## Query parameters

- `useWeightedScoring` boolean
- `page` integer
- `page_size` integer
- `sort` string[]
- `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

- QueryImagesByBenchmarkEndpointOutput — The queried per-image ratings output.
  - `items` QueryImagesByBenchmarkEndpointOutputPrompt[], required — The prompts of this page, each with its ranked images.
    - `promptIdentifier` string, required
    - `promptId` string, nullable
    - `englishPrompt` string, nullable
    - `originalPrompt` string, nullable
    - `promptAsset` union
      - IAssetFileAsset
        - `_t` 'FileAsset', required
        - `fileName` string, required
        - `metadata` MetadataModelCollection, required
        - `identifier` string, required
      - IAssetMultiAsset
        - `_t` 'MultiAsset', required
        - `assets` IAsset[], required
          - union
            - object
              - …
            - object
              - …
            - object
              - …
            - object
              - …
        - `metadata` MetadataModelCollection, required
        - `identifier` string, required
      - IAssetNullAsset
        - `_t` 'NullAsset', required
        - `metadata` MetadataModelCollection, required
        - `identifier` string, required
      - IAssetTextAsset
        - `_t` 'TextAsset', required
        - `text` string, required
        - `metadata` MetadataModelCollection, required
        - `identifier` string, required
    - `images` QueryImagesByBenchmarkEndpointOutputImage[], required
      - `sampleId` string, required
      - `participantId` string, required
      - `participantName` string, nullable
      - `label` string, required
      - `asset` union
        - IAssetFileAsset
          - `_t` 'FileAsset', required
          - `fileName` string, required
          - `metadata` MetadataModelCollection, required
          - `identifier` string, required
        - IAssetMultiAsset
          - `_t` 'MultiAsset', required
          - `assets` IAsset[], required
            - union
              - …
          - `metadata` MetadataModelCollection, required
          - `identifier` string, required
        - IAssetNullAsset
          - `_t` 'NullAsset', required
          - `metadata` MetadataModelCollection, required
          - `identifier` string, required
        - IAssetTextAsset
          - `_t` 'TextAsset', required
          - `text` string, required
          - `metadata` MetadataModelCollection, required
          - `identifier` string, required
      - `responseCount` integer, required
      - `rating` number, double, nullable, required
      - `rank` integer, required
    - `index` string[], required
    - `columns` string[], required
    - `data` array[], required
      - number[]
    - `votes` array[], required
      - number[]
  - `totalResponses` integer, required — Total raw human responses behind the corpus under the current filter.
  - `distinctMatchups` integer, required — Distinct compared image pairs in the corpus under the current filter.
  - `totalPrompts` integer, required — The number of prompts the filter leaves rankable — the paging total.
  - `page` integer, required — The 1-based page index.
  - `pageSize` integer, required — The page size in prompts.

## 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/d779de93a5ee/schema)