> ## Documentation Index
> Fetch the complete documentation index at: https://docs.coreweave.com/llms.txt
> Use this file to discover all available pages before exploring further.

# List evaluations



## OpenAPI

````yaml /openapi/model-distillation/management.openapi.yaml get /evals
openapi: 3.1.0
info:
  title: Model Distillation Management API
  version: 1.0.0
  description: |
    Manage providers, tasks, routing versions, datasets, relabeling, fine-tunes,
    evaluations, analytics, and closed-loop training Automation. This is the
    same API used by Model Distillation Studio.
servers:
  - url: https://distillation.training.wandb.ai/v1
    description: Production
security:
  - WandbApiKey: []
tags:
  - name: Providers
    description: OpenAI-compatible endpoints, credentials, model catalogs, and pricing.
  - name: Tasks
    description: Stable task identity and task-level information.
  - name: Routing
    description: Versioned model targets, weights, and request parameters.
  - name: Datasets
    description: >-
      Reproducible data snapshots, entries, relabeling, and reusable model
      outputs.
  - name: Fine-tunes
    description: Supervised fine-tuning jobs and hosted model artifacts.
  - name: Evaluations
    description: Head-to-head, exact-match, and categorization evaluations.
  - name: Automation
    description: Closed-loop dataset, sweep, evaluation, and promotion runs.
  - name: Analytics
    description: Task traffic, token, error, and estimated-cost read models.
  - name: Studio preferences
    description: Per-task display preferences used by Studio.
paths:
  /evals:
    parameters:
      - $ref: '#/components/parameters/WandbEntity'
    get:
      tags:
        - Evaluations
      summary: List evaluations
      operationId: listEvals
      parameters:
        - name: task_alias
          in: query
          description: Only return evaluations for this task alias.
          required: false
          schema:
            type: string
      responses:
        '200':
          description: Visible evaluations with live aggregate progress.
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/Eval'
        default:
          $ref: '#/components/responses/Error'
components:
  parameters:
    WandbEntity:
      name: Wandb-Entity
      in: header
      required: false
      description: >-
        Accessible personal or team entity. Omit to use the API key's default
        entity.
      schema:
        type: string
  schemas:
    Eval:
      type: object
      additionalProperties: true
      required:
        - id
        - dataset_id
        - name
        - spec
        - participants
        - sample_size
        - status
        - progress
        - created_at
        - updated_at
      properties:
        id:
          type: string
          format: uuid
        dataset_id:
          type: string
          format: uuid
        name:
          type: string
        spec:
          $ref: '#/components/schemas/EvalSpec'
        participants:
          type: array
          items:
            $ref: '#/components/schemas/EvalParticipant'
        reference:
          oneOf:
            - $ref: '#/components/schemas/EvalParticipant'
            - type: 'null'
        sample_size:
          type: integer
        status:
          type: string
          enum:
            - queued
            - running
            - completed
            - failed
            - stale
        progress:
          type: object
          required:
            - total
            - queued
            - running
            - completed
            - failed
          properties:
            total:
              type: integer
            queued:
              type: integer
            running:
              type: integer
            completed:
              type: integer
            failed:
              type: integer
        results:
          oneOf:
            - $ref: '#/components/schemas/JsonObject'
            - type: 'null'
        failure_summary:
          type: object
          additionalProperties: true
        created_at:
          type: string
          format: date-time
        updated_at:
          type: string
          format: date-time
    EvalSpec:
      oneOf:
        - type: object
          additionalProperties: false
          required:
            - type
            - judge_model_ref
          properties:
            type:
              type: string
              const: h2h_judge
            judge_model_ref:
              $ref: '#/components/schemas/ModelRef'
            judge_prompt:
              type: string
              minLength: 1
        - type: object
          additionalProperties: false
          required:
            - type
          properties:
            type:
              type: string
              const: exact_match
        - type: object
          additionalProperties: false
          required:
            - type
            - field
          properties:
            type:
              type: string
              const: categorization
            field:
              type: string
              minLength: 1
              maxLength: 256
    EvalParticipant:
      oneOf:
        - type: object
          additionalProperties: false
          required:
            - kind
          properties:
            kind:
              type: string
              const: original
        - type: object
          additionalProperties: false
          required:
            - kind
            - relabel_run_id
          properties:
            kind:
              type: string
              const: relabel
            relabel_run_id:
              type: string
              format: uuid
        - type: object
          additionalProperties: false
          required:
            - kind
            - model_ref
          properties:
            kind:
              type: string
              enum:
                - model
                - provider
            model_ref:
              $ref: '#/components/schemas/ModelRef'
    JsonObject:
      type: object
      additionalProperties: true
    ErrorResponse:
      type: object
      required:
        - error
      properties:
        error:
          type: object
          required:
            - message
            - type
          properties:
            message:
              type: string
            type:
              type: string
      example:
        error:
          message: Task 'missing' not found in entity 'your-team'
          type: not_found
    ModelRef:
      type: string
      pattern: ^[a-z0-9][a-z0-9_-]{0,63}/\S+$
      example: openai/gpt-5.6-sol
  responses:
    Error:
      description: Request failed.
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  securitySchemes:
    WandbApiKey:
      type: http
      scheme: bearer
      bearerFormat: W&B API key
      description: A personal or service-account W&B API key.

````