{
  "site": {
    "name": "Openbenchmarks for Agents",
    "url": "https://openbenchmarks.com",
    "description": "Open benchmarks for Agents - verified benchmarks for build vs buy decisions on AI agent tooling."
  },
  "last_updated": "2026-06-23T11:00:00.000Z",
  "benchmarks": [
    {
      "slug": "technographics",
      "name": "Technographics Benchmark",
      "description": "Head-to-head benchmark for technographics providers (BuiltWith, TheirStack, Apollo, Clay, Crustdata, Sumble, ZoomInfo). Providers return tools per company bucketed into 8 canonical departments; ranked by category coverage with consensus, breadth, and cost per tool as secondary signals. No internal ground truth.",
      "page_url": "https://openbenchmarks.com/technographics",
      "api_url": "https://openbenchmarks.com/api/benchmarks/technographics",
      "status": "live",
      "provider_count": 9,
      "canonical_categories": [
        "engineering",
        "data",
        "sales",
        "marketing",
        "finance",
        "hr",
        "support",
        "ops"
      ],
      "winners": {
        "highest_category_coverage": {
          "provider": "OpenFunnel",
          "category_coverage_pct": 100,
          "categories_covered": 8
        }
      }
    },
    {
      "slug": "lookalikes",
      "name": "Lookalike Benchmark",
      "description": "Head-to-head benchmark for company lookalike APIs (Ocean.io, ZoomInfo, Exa, Parallel, OpenFunnel, PredictLeads). Each vendor returns its top-K lookalikes per seed company; an LLM judge scores every returned company for relevance. Cell value = Precision@K, headline metric = avg Precision@K across the seed cohort.",
      "page_url": "https://openbenchmarks.com/lookalikes",
      "api_url": "https://openbenchmarks.com/api/benchmarks/lookalikes",
      "source_repo": "https://github.com/openbenchmarks-labs/lookalikes",
      "status": "live",
      "provider_count": 5,
      "canonical_categories": [
        "b2b-saas",
        "devtools",
        "ecommerce",
        "healthtech",
        "home-services",
        "trades",
        "real-estate",
        "fintech",
        "cybersecurity",
        "industrial",
        "logistics",
        "hospitality",
        "energy"
      ],
      "winners": {
        "highest_avg_precision_at_k": {
          "provider": "OpenFunnel",
          "avg_precision_at_k": 69.75,
          "seeds_judged": 24,
          "k": 100
        }
      }
    }
  ],
  "docs": {
    "openapi": "https://openbenchmarks.com/openapi.json",
    "llms": "https://openbenchmarks.com/llms.txt",
    "methodology": "https://openbenchmarks.com/technographics#methodology"
  },
  "mcp": {
    "name": "openbenchmarks",
    "url": "https://mcp.openbenchmarks.com/mcp",
    "transport": "http",
    "protocol_version": "2025-03-26",
    "capabilities": {
      "tools": true,
      "prompts": true,
      "resources": true,
      "tasks": true
    },
    "auth": {
      "type": "oauth2",
      "scopes": [
        "mcp"
      ],
      "dynamic_registration": true,
      "metadata_url": "https://mcp.openbenchmarks.com/.well-known/oauth-authorization-server"
    },
    "discovery": "https://openbenchmarks.com/.well-known/mcp.json",
    "documentation": "https://openbenchmarks.com/llms.txt",
    "description": "Openbenchmarks MCP server - connect Claude, ChatGPT, Cursor and other MCP clients to the public benchmark data via tools, prompts, and resources. OAuth 2.1 with dynamic client registration."
  }
}