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

# Run agent benchmark

> Run a multi-model benchmark on an agent's linked tests as a background job.



## OpenAPI

````yaml /api-reference/openapi.json post /agent-tests/agent/{agent_uuid}/benchmark
openapi: 3.1.0
info:
  title: Calibrate Public API
  version: 0.1.0
  description: Programmatic API for CI/automation. Pass your key in the `X-API-Key` header.
servers:
  - url: https://api.calibrate.artpark.ai
    description: Production
security: []
paths:
  /agent-tests/agent/{agent_uuid}/benchmark:
    post:
      tags:
        - agent-tests
      summary: Run agent benchmark
      description: >-
        Run a multi-model benchmark on an agent's linked tests as a background
        job.
      operationId: run_agent_benchmark_agent_tests_agent__agent_uuid__benchmark_post
      parameters:
        - name: agent_uuid
          in: path
          required: true
          schema:
            type: string
            description: Agent to benchmark
            examples:
              - f47ac10b-58cc-4372-a567-0e02b2c3d479
            title: Agent Uuid
          description: Agent to benchmark
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/BenchmarkRequest'
      responses:
        '200':
          description: Successful Response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AgentTestRunCreateResponse'
        '422':
          description: Validation Error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/HTTPValidationError'
      security:
        - ApiKeyAuth: []
components:
  schemas:
    BenchmarkRequest:
      properties:
        models:
          items:
            type: string
          type: array
          title: Models
          description: Model names to benchmark
          examples:
            - - openai/gpt-4.1
              - anthropic/claude-sonnet-4
        test_uuids:
          anyOf:
            - items:
                type: string
              type: array
            - type: 'null'
          title: Test Uuids
          description: >-
            A subset of the agent's linked tests to benchmark. Each ID must be
            linked to the agent. Omit to run all linked tests
          examples:
            - - b1c2d3e4-f5a6-7890-bcde-f12345678901
      type: object
      required:
        - models
      title: BenchmarkRequest
    AgentTestRunCreateResponse:
      properties:
        task_id:
          type: string
          maxLength: 36
          minLength: 36
          title: Task Id
          description: Test run job ID. Poll it for status and results
          examples:
            - a3b2c1d0-e5f4-3210-abcd-ef1234567890
        status:
          type: string
          enum:
            - queued
            - in_progress
          title: Status
          description: Current status of the run
      type: object
      required:
        - task_id
        - status
      title: AgentTestRunCreateResponse
    HTTPValidationError:
      properties:
        detail:
          items:
            $ref: '#/components/schemas/ValidationError'
          type: array
          title: Detail
      type: object
      title: HTTPValidationError
    ValidationError:
      properties:
        loc:
          items:
            anyOf:
              - type: string
              - type: integer
          type: array
          title: Location
        msg:
          type: string
          title: Message
        type:
          type: string
          title: Error Type
      type: object
      required:
        - loc
        - msg
        - type
      title: ValidationError
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: X-API-Key
      description: API key for authentication

````