Skip to content
ProductArena

How ElevenLabs Agents’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score28/100

Agent-ready 60.0 × 0.30 = 18.00

API quality 3.4 × 0.20 = 0.68

Openness 8.4 × 0.20 = 1.68

Built-in AI 39.8 × 0.15 = 5.97

Automation 13.5 × 0.15 = 2.02

(18.00 + 0.68 + 1.68 + 5.97 + 2.02) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 28.35 ÷ 1.00 = 28.4

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready60.0/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [probe] https://elevenlabs.io/llms.txt“PROBE llms.txt: HTTP 200 at https://elevenlabs.io/llms.txt # ElevenLabs ElevenLabs is an AI research and product company transforming how we interact with technology. We launched”
  • [probe] https://elevenlabs.io/docs/eleven-agents/overview.md“PROBE docs-md: HTTP 200 at https://elevenlabs.io/docs/eleven-agents/overview.md > This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“ElevenLabs Agents are managed either through the ElevenAgents dashboard, the ElevenLabs API, the Agents CLI or the hosted MCP server.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“we'll start by creating an agent via the API or the web dashboard”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/agent-testing.md“Agent testing lets you verify conversational responses, tool usage, and full multi-turn outcomes before you deploy.”
  • [probe] https://www.npmjs.com/package/@elevenlabs/cli“PROBE runtime (recorded 2026-09-05): `npx -y @elevenlabs/cli --version` printed `elevenlabs 1.1.0` keylessly — the official ElevenLabs CLI (successor to @elevenlabs/agents-cli, which now redirects to it) installs and runs from npm without an account.”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 8 (quality) × 1.0 (full) = 24.0 of 30 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/mcp.md“ElevenLabs allows you to connect your conversational agents to external MCP servers. This enables your agents to: Access and process information from various data sources via the MCP server”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/mcp.md“ElevenLabs allows you to connect your conversational agents to external MCP servers.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/mcp.md“Access and process information from various data sources via the MCP server”

Connect an agent via an official MCP serverweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“ElevenLabs Agents are managed either through the ElevenAgents dashboard, the ElevenLabs API, the Agents CLI or the hosted MCP server.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“an assistant such as Claude can create, configure, and manage the agents in your workspace through natural language, with nothing to install or run locally”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“connect the hosted MCP server to Claude or any other MCP client to create and manage agents through natural language”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“create, configure, and manage the agents in your workspace through natural language, with nothing to install or run locally”
  • [probe] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp“official MCP server documented at https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp”
  • [probe] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp“PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.elevenlabs.io/v1/mcp returned HTTP 401 with `WWW-Authenticate: Bearer resource_metadata="https://api.us.elevenlabs.io/.well-known/oauth-protected-resource"` — the documented hosted MCP endpoint is live and speaks the MCP OAuth flow.”

Use an official CLIweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“ElevenLabs Agents are managed either through the ElevenAgents dashboard, the ElevenLabs API, the Agents CLI or the hosted MCP server.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“Use the ElevenLabs agents skill to build and manage voice agents from your AI coding assistant: npx skills add elevenlabs/skills --skill agents”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“Use the ElevenLabs agents skill to build and manage voice agents from your AI coding assistant”
  • [probe] https://www.npmjs.com/package/@elevenlabs/cli“PROBE runtime (recorded 2026-09-05): `npx -y @elevenlabs/cli --version` printed `elevenlabs 1.1.0` keylessly — the official ElevenLabs CLI (successor to @elevenlabs/agents-cli, which now redirects to it) installs and runs from npm without an account.”

Drive the product through a documented public APIweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“ElevenLabs Agents are managed either through the ElevenAgents dashboard, the ElevenLabs API, the Agents CLI or the hosted MCP server.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“we'll start by creating an agent via the API or the web dashboard”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/build/overview.md“Enable agents to call clients & APIs to perform actions”
  • [probe] https://www.npmjs.com/package/@elevenlabs/cli“PROBE runtime (recorded 2026-09-05): `npx -y @elevenlabs/cli --version` printed `elevenlabs 1.1.0` keylessly — the official ElevenLabs CLI (successor to @elevenlabs/agents-cli, which now redirects to it) installs and runs from npm without an account.”
  • [probe] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp“PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.elevenlabs.io/v1/mcp returned HTTP 401 with `WWW-Authenticate: Bearer resource_metadata="https://api.us.elevenlabs.io/.well-known/oauth-protected-resource"` — the documented hosted MCP endpoint is live and speaks the MCP OAuth flow.”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/build/overview.md“Secure agent access | Authentication | Implement custom authentication for protected agent access”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/build/overview.md“Implement custom authentication for protected agent access”
  • [probe] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp“PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.elevenlabs.io/v1/mcp returned HTTP 401 with `WWW-Authenticate: Bearer resource_metadata="https://api.us.elevenlabs.io/.well-known/oauth-protected-resource"` — the documented hosted MCP endpoint is live and speaks the MCP OAuth flow.”

Build against official SDKsweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“ElevenLabs Agents are managed either through the ElevenAgents dashboard, the ElevenLabs API, the Agents CLI or the hosted MCP server.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“we'll start by creating an agent via the API or the web dashboard”
  • [probe] https://www.npmjs.com/package/@elevenlabs/cli“PROBE runtime (recorded 2026-09-05): `npx -y @elevenlabs/cli --version` printed `elevenlabs 1.1.0` keylessly — the official ElevenLabs CLI (successor to @elevenlabs/agents-cli, which now redirects to it) installs and runs from npm without an account.”

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/webhook-tools.md“Tools give your assistant the ability to make external function calls to third party apps so you can get real-time information.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools.md“Tools allow ElevenLabs agents to perform actions beyond generating text responses.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/webhook-tools.md“allow an assistant to trigger authenticated actions based on the conversation, like scheduling meetings or initiating order returns”

Agent-ready = 126.0 ÷ 210 × 100 = 60.0

API quality3.4/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 4 (quality) × 0.6 (partial) = 2.4 of 10 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/agent-testing.md“Agent testing lets you verify conversational responses, tool usage, and full multi-turn outcomes before you deploy.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/agent-testing.md“Agent testing lets you verify conversational responses, tool usage, and full multi-turn outcomes before you deploy”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools.md“Custom JavaScript executed in a sandboxed environment on ElevenLabs' infrastructure.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools.md“Custom JavaScript executed in a sandboxed environment on ElevenLabs' infrastructure”

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

API quality = 2.4 ÷ 70 × 100 = 3.4

Openness8.4/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 7 (quality) × 0.6 (partial) = 8.4 of 20 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“ElevenLabs Agents are managed either through the ElevenAgents dashboard, the ElevenLabs API, the Agents CLI or the hosted MCP server.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“we'll start by creating an agent via the API or the web dashboard”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“create, configure, and manage the agents in your workspace through natural language, with nothing to install or run locally”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/build/overview.md“Build multi-step workflows with visual workflow builder”
  • [probe] https://www.npmjs.com/package/@elevenlabs/cli“PROBE runtime (recorded 2026-09-05): `npx -y @elevenlabs/cli --version` printed `elevenlabs 1.1.0` keylessly — the official ElevenLabs CLI (successor to @elevenlabs/agents-cli, which now redirects to it) installs and runs from npm without an account.”

Export all of my data in open formats and leaveweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“ElevenLabs Agents are managed either through the ElevenAgents dashboard, the ElevenLabs API, the Agents CLI or the hosted MCP server.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“an assistant such as Claude can create, configure, and manage the agents in your workspace through natural language, with nothing to install or run locally”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“create, configure, and manage the agents in your workspace through natural language, with nothing to install or run locally”

Openness = 8.4 ÷ 100 × 100 = 8.4

Built-in AI39.8/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/agent-analysis.md“Success evaluation: Define custom criteria to assess conversation quality, goal achievement, and customer satisfaction”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/agent-analysis.md“Data collection: Extract specific data points from conversations such as contact information, issue details, or any structured information”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/agent-analysis.md“Sentiment analysis: Understand user sentiment across completed conversations”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/agent-analysis.md“Searching conversations: Find messages by keyword or meaning across your conversation history.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/agent-analysis.md“Define custom criteria to assess conversation quality, goal achievement, and customer satisfaction”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/agent-analysis.md“Extract structured information from conversations such as contact details and business data”

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/build/overview.md“Build multi-step workflows with visual workflow builder”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/build/overview.md“Enable agents to call clients & APIs to perform actions”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/webhook-tools.md“Tools give your assistant the ability to make external function calls to third party apps so you can get real-time information.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/webhook-tools.md“allow an assistant to trigger authenticated actions based on the conversation, like scheduling meetings or initiating order returns”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/mcp.md“ElevenLabs allows you to connect your conversational agents to external MCP servers. This enables your agents to: Access and process information from various data sources via the MCP server”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“we'll start by creating an agent via the API or the web dashboard”

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“an assistant such as Claude can create, configure, and manage the agents in your workspace through natural language, with nothing to install or run locally”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“an assistant such as Claude can create, configure, and manage the agents in your workspace through natural language”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“connect the hosted MCP server to Claude or any other MCP client to create and manage agents through natural language”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“create, configure, and manage the agents in your workspace through natural language, with nothing to install or run locally”
  • [probe] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp“PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.elevenlabs.io/v1/mcp returned HTTP 401 with `WWW-Authenticate: Bearer resource_metadata="https://api.us.elevenlabs.io/.well-known/oauth-protected-resource"` — the documented hosted MCP endpoint is live and speaks the MCP OAuth flow.”

Operate the product with natural-language commandsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“an assistant such as Claude can create, configure, and manage the agents in your workspace through natural language, with nothing to install or run locally”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“an assistant such as Claude can create, configure, and manage the agents in your workspace through natural language”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/quickstart.md“connect the hosted MCP server to Claude or any other MCP client to create and manage agents through natural language”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp.md“create, configure, and manage the agents in your workspace through natural language, with nothing to install or run locally”
  • [probe] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp“PROBE runtime (recorded 2026-09-05): keyless JSON-RPC initialize POST to the hosted MCP server https://api.elevenlabs.io/v1/mcp returned HTTP 401 with `WWW-Authenticate: Bearer resource_metadata="https://api.us.elevenlabs.io/.well-known/oauth-protected-resource"` — the documented hosted MCP endpoint is live and speaks the MCP OAuth flow.”
  • [probe] https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp“official MCP server documented at https://elevenlabs.io/docs/eleven-agents/operate/hosted-mcp”

Built-in AI = 35.8 ÷ 90 × 100 = 39.8

Automation13.5/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 6 (quality) × 0.6 (partial) = 10.8 of 30 max

  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/build/overview.md“Enable agents to call clients & APIs to perform actions”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/webhook-tools.md“Tools give your assistant the ability to make external function calls to third party apps so you can get real-time information.”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/webhook-tools.md“allow an assistant to trigger authenticated actions based on the conversation, like scheduling meetings or initiating order returns”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/build/overview.md“Build multi-step workflows with visual workflow builder”
  • [claimed-docs] https://elevenlabs.io/docs/eleven-agents/customization/tools/mcp.md“ElevenLabs allows you to connect your conversational agents to external MCP servers. This enables your agents to: Access and process information from various data sources via the MCP server”

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Automation = 10.8 ÷ 80 × 100 = 13.5