Skip to content
ProductArena

How Tavily’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 Score39/100

Agent-ready 58.1 × 0.30 = 17.43

API quality 12.0 × 0.20 = 2.40

Openness 14.0 × 0.20 = 2.80

Built-in AI 36.0 × 0.15 = 5.40

Automation 70.0 × 0.15 = 10.50

(17.43 + 2.40 + 2.80 + 5.40 + 10.50) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 38.53 ÷ 1.00 = 38.5

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-ready58.1/100×0.30 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) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [probe] https://docs.tavily.com/llms.txt“PROBE llms.txt: HTTP 200 at https://docs.tavily.com/llms.txt # Tavily Docs > Tavily is the web layer for AI agents: real-time web search, content extraction, site crawling, site ma”
  • [claimed-docs] https://docs.tavily.com/llms.txt“tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React vs Svelte for production apps"”
  • [claimed-docs] https://docs.tavily.com“Read and execute tavily.com/agent-setup/SKILL.md”
  • [claimed-docs] https://docs.tavily.com“Let your coding agent install and configure Tavily for you.”
  • [claimed-docs] https://docs.tavily.com/documentation/mcp“Compatible with both Cursor and Claude Desktop! Tavily MCP is also compatible with any MCP client.”
  • [probe] https://docs.tavily.com/documentation/mcp“official MCP server documented at https://docs.tavily.com/documentation/mcp”

Run the product headlessly / in CI for automationweight 2

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

  • [claimed-docs] https://docs.tavily.com“pip install tavily-python”
  • [claimed-docs] https://docs.tavily.com/llms.txt“tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React vs Svelte for production apps"”
  • [claimed-docs] https://docs.tavily.com/sdk/python/quick-start.md“The Python SDK allows for easy interaction with the Tavily API, offering the full range of our search functionality directly from your Python programs.”
  • [claimed-docs] https://docs.tavily.com/sdk/javascript/quick-start.md“Tavily's JavaScript SDK allows for easy interaction with the Tavily API, offering the full range of our search and extract functionalities directly from your JavaScript and TypeScript programs.”
  • [claimed-docs] https://docs.tavily.com/documentation/rate-limits“Environment Requests per minute (RPM) Development 100 Production 1,000”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/logs.md“Retrieve per-request usage logs for the API keys under your account or organization.”
  • [claimed-docs] https://docs.tavily.com“tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY") response = tavily_client.search("Who is Leo Messi?")”

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

n/a — not applicable to this product: excluded from numerator and denominator

  • [claimed-docs] https://docs.tavily.com/documentation/mcp“The Tavily MCP server provides: Seamless interaction with the tavily-search and tavily-extract tools”
  • [claimed-docs] https://docs.tavily.com/documentation/mcp“The Tavily MCP server provides: * Seamless interaction with the tavily-search and tavily-extract tools”
  • [claimed-docs] https://docs.tavily.com/documentation/mcp.md“Compatible with both [Cursor](https://cursor.sh) and [Claude Desktop](https://claude.ai/download)! Tavily MCP is also compatible with any MCP client.”
  • [probe] https://docs.tavily.com/documentation/mcp“official MCP server documented at https://docs.tavily.com/documentation/mcp”

Connect an agent via an official MCP serverweight 3

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

  • [claimed-docs] https://docs.tavily.com/documentation/mcp“The Tavily MCP server provides: Seamless interaction with the tavily-search and tavily-extract tools”
  • [claimed-docs] https://docs.tavily.com/documentation/mcp“Compatible with both Cursor and Claude Desktop! Tavily MCP is also compatible with any MCP client.”
  • [claimed-docs] https://docs.tavily.com/documentation/mcp“The Tavily MCP server provides: * Seamless interaction with the tavily-search and tavily-extract tools”
  • [claimed-docs] https://docs.tavily.com/documentation/mcp.md“Compatible with both [Cursor](https://cursor.sh) and [Claude Desktop](https://claude.ai/download)! Tavily MCP is also compatible with any MCP client.”
  • [probe] https://docs.tavily.com/documentation/mcp“official MCP server documented at https://docs.tavily.com/documentation/mcp”

Use an official CLIweight 2

2 (weight) × 3 (quality) × 0.6 (partial) = 3.6 of 20 max

  • [claimed-docs] https://docs.tavily.com/llms.txt“tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React vs Svelte for production apps"”

Drive the product through a documented public APIweight 3

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

  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/search.md“Execute a search query using Tavily Search.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/extract.md“Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_results.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/crawl.md“Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent discovery.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/map.md“Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensive site maps.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/research.md“Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detailed research report.”
  • [claimed-docs] https://docs.tavily.com/sdk/python/quick-start.md“The Python SDK allows for easy interaction with the Tavily API, offering the full range of our search functionality directly from your Python programs.”
  • [claimed-docs] https://docs.tavily.com/sdk/javascript/quick-start.md“Tavily's JavaScript SDK allows for easy interaction with the Tavily API, offering the full range of our search and extract functionalities directly from your JavaScript and TypeScript programs.”
  • [claimed-docs] https://docs.tavily.com/documentation/rate-limits“Environment Requests per minute (RPM) Development 100 Production 1,000”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/usage.md“Get API key and account usage details”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/logs.md“Retrieve per-request usage logs for the API keys under your account or organization.”
  • [github] https://github.com/tavily-ai/tavily-python“You can try Tavily without an API key. Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API.”
  • [probe] https://docs.tavily.com/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/api/openapi.json, https://docs.tavily.com/.well-known/openapi.json)”

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://docs.tavily.com/sdk/python/reference.md“You can attach a Project ID to your client to organize and track API usage by project. This is useful when a single API key is used across multiple projects.”
  • [claimed-docs] https://docs.tavily.com/sdk/python/reference.md“You can attach session and user identifiers to your client for attribution and analytics across multi-step interactions and agent workflows.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/usage.md“Get API key and account usage details”

Build against official SDKsweight 2

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

  • [claimed-docs] https://docs.tavily.com“pip install tavily-python”
  • [claimed-docs] https://docs.tavily.com/sdk/python/quick-start.md“The Python SDK allows for easy interaction with the Tavily API, offering the full range of our search functionality directly from your Python programs.”
  • [claimed-docs] https://docs.tavily.com/sdk/javascript/quick-start.md“Tavily's JavaScript SDK allows for easy interaction with the Tavily API, offering the full range of our search and extract functionalities directly from your JavaScript and TypeScript programs.”
  • [claimed-docs] https://docs.tavily.com“tavily_client = TavilyClient(api_key="tvly-YOUR_API_KEY") response = tavily_client.search("Who is Leo Messi?")”
  • [claimed-docs] https://docs.tavily.com“response = tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
  • [claimed-docs] https://docs.tavily.com“response = tavily_client.map("https://docs.tavily.com")”
  • [claimed-docs] https://docs.tavily.com“response = tavily_client.research("What are the latest developments in AI?")”
  • [github] https://github.com/tavily-ai/tavily-python“Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API. Keyless mode supports `search()` and `extract()` only”
  • [claimed-docs] https://docs.tavily.com/sdk/python/reference.md“You can attach a Project ID to your client to organize and track API usage by project. This is useful when a single API key is used across multiple projects.”
  • [claimed-docs] https://docs.tavily.com/sdk/python/reference.md“You can attach session and user identifiers to your client for attribution and analytics across multi-step interactions and agent workflows.”
  • [claimed-docs] https://docs.tavily.com/sdk/javascript/reference.md“If you would like to specify a proxy to be used when making requests, you can do so by passing in a proxy parameter on client instantiation.”
  • [probe] https://docs.tavily.com/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/api/openapi.json, https://docs.tavily.com/.well-known/openapi.json)”

Subscribe to events via webhooksweight 2

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

  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/research-get.md“Retrieve the status and results of a research task using its request ID.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/research-streaming.md“When using the Tavily Research API, you can stream responses in real-time by setting `stream: true` in your request.”
  • [probe] https://docs.tavily.com/llms.txt“PROBE llms.txt: HTTP 200 at https://docs.tavily.com/llms.txt # Tavily Docs > Tavily is the web layer for AI agents: real-time web search, content extraction, site crawling, site ma”
  • [probe] https://docs.tavily.com/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/api/openapi.json, https://docs.tavily.com/.well-known/openapi.json)”

Agent-ready = 104.6 ÷ 180 × 100 = 58.1

API quality12.0/100×0.20 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) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/search.md“Execute a search query using Tavily Search.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/extract.md“Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_results.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/crawl.md“Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent discovery.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/map.md“Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensive site maps.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/research.md“Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detailed research report.”
  • [probe] https://docs.tavily.com/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/api/openapi.json, https://docs.tavily.com/.well-known/openapi.json)”

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

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

  • [probe] https://docs.tavily.com/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/api/openapi.json, https://docs.tavily.com/.well-known/openapi.json)”

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://docs.tavily.com/documentation/rate-limits“Environment Requests per minute (RPM) Development 100 Production 1,000”
  • [claimed-docs] https://docs.tavily.com/documentation/rate-limits“`Production` 1,000”
  • [github] https://github.com/tavily-ai/tavily-python“Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API. Keyless mode supports `search()` and `extract()` only”
  • [github] https://github.com/tavily-ai/tavily-python“You can try Tavily without an API key. Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API.”
  • [github] https://github.com/tavily-ai/tavily-python“You can try Tavily without an API key. Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API. Keyless mode supports `search()` and `extract()` only”

Rely on versioned APIs with a documented deprecation policyweight 2

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

  • [probe] https://docs.tavily.com/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/api/openapi.json, https://docs.tavily.com/.well-known/openapi.json)”

API quality = 8.4 ÷ 70 × 100 = 12.0

Openness14.0/100×0.20 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) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://docs.tavily.com“tavily_client.search("Who is Leo Messi?")”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/extract“Extract web page content from one or more specified URLs using Tavily Extract.”
  • [claimed-docs] https://docs.tavily.com“tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
  • [claimed-docs] https://docs.tavily.com“tavily_client.research("What are the latest developments in AI?")”
  • [github] https://github.com/tavily-ai/tavily-python“Map lets you discover and visualize the structure of a website starting from a base URL.”
  • [github] https://github.com/tavily-ai/tavily-python“context = tavily_client.get_search_context(query="What happened during the Burning Man floods?")”
  • [github] https://github.com/tavily-ai/tavily-python“answer = tavily_client.qna_search(query="Who is Leo Messi?")”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/search.md“Execute a search query using Tavily Search.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/extract.md“Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_results.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/crawl.md“Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent discovery.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/map.md“Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensive site maps.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/research.md“Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detailed research report.”
  • [claimed-docs] https://docs.tavily.com/llms.txt“tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React vs Svelte for production apps"”
  • [probe] https://docs.tavily.com/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.tavily.com/openapi.json, https://docs.tavily.com/swagger.json, https://docs.tavily.com/api/openapi.json, https://docs.tavily.com/.well-known/openapi.json)”

Export all of my data in open formats and leaveweight 3

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

  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/usage.md“Get API key and account usage details”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/logs.md“Retrieve per-request usage logs for the API keys under your account or organization.”

Read the product's source under an open licenseweight 2

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

  • [github] https://github.com/tavily-ai/tavily-python“Map lets you discover and visualize the structure of a website starting from a base URL.”
  • [github] https://github.com/tavily-ai/tavily-python“Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API. Keyless mode supports `search()` and `extract()` only”

Self-host the core productweight 3

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

  • [claimed-docs] https://www.tavily.com/pricing“1,000 API credits / month ... No credit card required”
  • [github] https://github.com/tavily-ai/tavily-python“Instantiate `TavilyClient()` with no arguments and the SDK runs in keyless mode against the public Tavily API. Keyless mode supports `search()` and `extract()` only”
  • [claimed-docs] https://docs.tavily.com/documentation/rate-limits“Environment Requests per minute (RPM) Development 100 Production 1,000”

Openness = 14.0 ÷ 100 × 100 = 14.0

Built-in AI36.0/100×0.15 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

n/a — not applicable to this product: excluded from numerator and denominator

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

Set up automations that run autonomously in the backgroundweight 2

n/a — not applicable to this product: excluded from numerator and denominator

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

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

n/a — not applicable to this product: excluded from numerator and denominator

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

Operate the product with natural-language commandsweight 2

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

  • [claimed-docs] https://docs.tavily.com“tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
  • [claimed-docs] https://docs.tavily.com“response = tavily_client.crawl("https://docs.tavily.com", instructions="Find all pages on the Python SDK")”
  • [claimed-docs] https://docs.tavily.com/llms.txt“tvly search "latest AI news" tvly extract "https://example.com" tvly crawl "https://docs.example.com" --depth 2 tvly research "compare React vs Svelte for production apps"”
  • [claimed-docs] https://docs.tavily.com/documentation/mcp“The Tavily MCP server provides: Seamless interaction with the tavily-search and tavily-extract tools”
  • [probe] https://docs.tavily.com/documentation/mcp“official MCP server documented at https://docs.tavily.com/documentation/mcp”
  • [github] https://github.com/tavily-ai/tavily-python“Tavily Research Research lets you create comprehensive research reports on any topic, with aut”

Built-in AI = 7.2 ÷ 20 × 100 = 36.0

Automation70.0/100×0.15 of the PA blend

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

Perform bulk operations across many items at onceweight 2

2 (weight) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/extract.md“Extract content from one URL or batch up to 20 URLs in one request. Successful URLs appear in results; per-URL failures appear in failed_results.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/crawl.md“Tavily Crawl is a graph-based website traversal tool that can explore hundreds of paths in parallel with built-in extraction and intelligent discovery.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/map.md“Tavily Map traverses websites like a graph and can explore hundreds of paths in parallel with intelligent discovery to generate comprehensive site maps.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/research.md“Tavily Research performs comprehensive research on a given topic by conducting multiple searches, analyzing sources, and generating a detailed research report.”
  • [claimed-docs] https://docs.tavily.com/documentation/api-reference/endpoint/research-get.md“Retrieve the status and results of a research task using its request ID.”
  • [github] https://github.com/tavily-ai/tavily-python“Crawl lets you traverse a website's content starting from a base URL.”
  • [github] https://github.com/tavily-ai/tavily-python“Tavily Research Research lets you create comprehensive research reports on any topic, with aut”

Define rules that trigger actions automatically on eventsweight 3

n/a — not applicable to this product: excluded from numerator and denominator

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

Schedule recurring jobs or workflowsweight 2

n/a — not applicable to this product: excluded from numerator and denominator

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

Version, review, and roll back my automationsweight 1

n/a — not applicable to this product: excluded from numerator and denominator

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

Automation = 14.0 ÷ 20 × 100 = 70.0