> ## Documentation Index > Fetch the complete documentation index at: https://docs.zelto.ai/llms.txt > Use this file to discover all available pages before exploring further. # List benchmarks > Benchmarks in the organization, most recently updated first, with their latest runs. ## OpenAPI ````yaml /docs-openapi.json get /v1/benchmarks openapi: 3.1.0 info: title: Zelto REST API version: v1 description: >- Programmatic access to your Zelto organization. Every endpoint is scoped to the organization the API key belongs to. Mint a key at Settings → Integrations → API integration. servers: - url: https://api.zelto.ai description: Production security: - bearerAuth: [] tags: - name: Monitors description: Filtered, asynchronous exports of stored monitor results. - name: Agents description: Voice and text agents normalised through Zelto's ingestion pipeline. - name: Conversations description: >- Phone calls, chats, and voicemails — plus their transcripts and recordings. - name: Customer Metrics description: >- Customer-provided evaluations attached to a conversation (requires metrics enabled). - name: Reviews description: Human review state for conversations. - name: Buckets description: Reviewer routing — group conversations for batched review. - name: Companies description: Clients or brands your agents work for, and their logos. - name: Findings description: >- Structured issues discovered during analysis, with optional conversation attachments and comments. - name: Experiments description: >- Prospective measurement of two externally routed prompt versions across independent monitor outcomes. - name: Organizations description: >- Headless org provisioning. Requires an admin/service API key (not a read-only org-scoped customer key). - name: AI providers description: >- Your organization's own (bring-your-own) AI provider keys. Monitors can run on them instead of Zelto's built-in models. Owner or admin keys only; the secret is write-only. - name: Benchmarks description: >- Repeatable evaluations of agent prompts, models and speech-to-text engines over a fixed set of cases, scored by Judges. paths: /v1/benchmarks: get: tags: - Benchmarks summary: List benchmarks description: >- Benchmarks in the organization, most recently updated first, with their latest runs. operationId: listBenchmarks parameters: - name: kind in: query required: false description: Only `llm` or only `stt` benchmarks. schema: type: string enum: - llm - stt - name: agentId in: query required: false description: >- Keep benchmarks assigned to any of these agents. Repeat the parameter for several. schema: type: array items: type: string format: uuid - name: archived in: query required: false description: >- Archived benchmarks: left out (default), included, or the only ones listed. schema: type: string enum: - exclude - include - only - $ref: '#/components/parameters/Limit' - $ref: '#/components/parameters/Cursor' responses: '200': description: Successful response. content: application/json: schema: type: object properties: data: type: array items: $ref: '#/components/schemas/BenchmarkSummary' nextCursor: description: Cursor for the next page, or null on the last page. type: - string - 'null' required: - data - nextCursor '400': $ref: '#/components/responses/ValidationFailed' '401': $ref: '#/components/responses/Unauthorized' components: parameters: Limit: name: limit in: query required: false description: >- Items per page. Default 50, max 200 (larger values are clamped to 200). Must be a positive integer; anything else is rejected with a 400 `invalid_parameter`. schema: type: integer minimum: 1 maximum: 200 default: 50 Cursor: name: cursor in: query required: false description: >- Opaque pagination cursor. Pass the `nextCursor` returned by the previous page, unchanged. A cursor this API did not issue is rejected with a 400 `invalid_parameter`. List endpoints also answer 400 `unknown_query_parameter` (listing the valid names) for any query parameter they do not accept, so a misspelled filter such as `agent_id` is never silently ignored. schema: type: string schemas: BenchmarkSummary: type: object properties: id: type: string name: type: string description: type: - string - 'null' kind: type: string enum: - llm - stt agents: type: array items: $ref: '#/components/schemas/BenchmarkAgentRef' caseCount: type: integer description: Active cases in the current published version. draftCaseCount: description: >- Cases the open draft would publish; null when the benchmark has no draft. anyOf: - type: integer - type: 'null' validatorKinds: type: array items: type: string enum: - judge - code - builtin runs: type: array items: $ref: '#/components/schemas/BenchmarkListRun' description: Most recent runs, newest first (at most 5). createdAt: type: string description: ISO 8601 timestamp. updatedAt: type: string description: ISO 8601 timestamp. archivedAt: anyOf: - type: string description: ISO 8601 timestamp. - type: 'null' settings: $ref: '#/components/schemas/BenchmarkSettings' language: type: - string - 'null' currentVersion: anyOf: - type: integer - type: 'null' hasDraftChanges: type: boolean required: - id - name - description - kind - agents - caseCount - validatorKinds - runs - createdAt - updatedAt description: One benchmark in the list. BenchmarkAgentRef: type: object properties: id: type: string name: type: string required: - id - name description: An agent the benchmark is assigned to. BenchmarkListRun: type: object properties: id: type: string number: type: integer status: type: string enum: - queued - running - completed - failed - cancelled - awaiting_approval - rejected totalCells: type: integer completedCells: type: integer failedCells: type: integer erroredCells: type: integer allErrored: type: boolean candidates: type: array items: $ref: '#/components/schemas/BenchmarkCandidate' results: type: array items: type: object properties: candidateId: type: string passRate: type: - number - 'null' wer: type: - number - 'null' p50LatencyMs: type: - number - 'null' costUsd: type: - number - 'null' required: - candidateId - passRate - wer - p50LatencyMs - costUsd estimatedCostUsd: type: number actualCostUsd: type: - number - 'null' createdBy: type: string createdByUser: $ref: '#/components/schemas/BenchmarkRunAuthor' createdAt: type: string description: ISO 8601 timestamp. finishedAt: anyOf: - type: string description: ISO 8601 timestamp. - type: 'null' required: - id - number - status - totalCells - completedCells - failedCells - erroredCells - allErrored - candidates - results - estimatedCostUsd - actualCostUsd - createdBy - createdByUser - createdAt - finishedAt description: >- A recent run as shown on the benchmarks list (full results: the runs endpoints). BenchmarkSettings: type: object properties: passBar: anyOf: - type: number minimum: 0 maximum: 1 - type: 'null' description: >- The goal: LLM minimum pass rate, STT maximum WER (both 0..1). Null = no goal. defaultRepeats: type: integer minimum: 1 maximum: 3 description: Repeats a new run starts with (LLM only). defaultCandidates: maxItems: 10 type: array items: type: object properties: model: type: string minLength: 1 maxLength: 200 agentVersionId: anyOf: - type: string minLength: 1 maxLength: 100 - type: 'null' required: - model - agentVersionId required: - passBar - defaultRepeats - defaultCandidates description: Benchmark-level run defaults. Not versioned. Error: type: object required: - error properties: error: type: string description: >- Short error name: `Unauthorized`, `Validation failed`, `Not found`, or a stable snake_case code you can match on, such as `unknown_query_parameter`, `invalid_parameter`, `payload_too_large` or `not_found`. message: type: string description: A plain-English sentence saying what is wrong and how to fix it. code: type: string description: >- Stable, machine-readable cause; match on this rather than on `error` or `message`. On a 401: `missing_credentials`, `malformed_credentials`, `ingest_key_not_allowed` (a write-only observability ingest key was used on an endpoint that needs an API key), `key_expired` or `invalid_credentials`. Elsewhere, for example: `not_found`, `invalid_parameter`, `unknown_query_parameter`, `missing_parameter`, `validation_failed`, `invalid_json`, `payload_too_large`, `conversation_not_found`, `plan_required`. hint: type: string description: >- The next step to try: where to find the right id, which parameters the endpoint takes, how to upgrade the plan, how to authenticate. parameter: type: string description: 'With `invalid_parameter`: the query parameter that was rejected.' unknown: type: array items: type: string description: >- With `unknown_query_parameter`: the parameters that were sent but are not accepted here. valid: type: array items: type: string description: >- With `unknown_query_parameter`: the parameters this endpoint accepts. details: type: object additionalProperties: true BenchmarkCandidate: type: object properties: id: type: string label: type: string model: type: string description: 'LLM: "openrouter/anthropic/claude-…"; STT: "deepgram/nova-3".' agentVersionId: description: LLM only. Null = the prompt as recorded on each case. type: - string - 'null' agentVersionLabel: type: - string - 'null' isReference: type: boolean required: - id - label - model - agentVersionId - agentVersionLabel description: 'What a run compares: a model plus a prompt source, or an STT engine.' BenchmarkRunAuthor: type: object properties: id: type: string name: type: string image: type: - string - 'null' required: - id - name - image description: An organization member. responses: ValidationFailed: description: >- The request body or query string failed validation. `code` says which kind (`validation_failed`, `invalid_json`, `invalid_parameter`, `unknown_query_parameter`, `missing_parameter`), and an enum filter names the allowed values in `valid` (every repeated value is checked, e.g. `?status=open&status=zz` is a 400). A `validation_failed` body also carries `message` (the first failing fields), `hint` (how to fix it, for example that a finding `description` is a TipTap JSON document and not a string) and `details` (field name to messages). content: application/json: schema: $ref: '#/components/schemas/Error' Unauthorized: description: >- Missing or invalid API key. The body names the cause in `code` (for example `ingest_key_not_allowed` when a write-only ingest key is used here) with a `message` and `hint`. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearerAuth: type: http scheme: bearer description: >- Send `Authorization: Bearer YOUR_API_KEY`. The key resolves to a single organization. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.