Skip to content

How Claude’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 Score29/100

Agent-ready 27.8 × 0.30 = 8.34

API quality 0.0 × 0.20 = 0.00

Openness 15.4 × 0.20 = 3.08

Built-in AI 85.6 × 0.15 = 12.84

Automation 29.0 × 0.15 = 4.35

(8.34 + 0.00 + 3.08 + 12.84 + 4.35) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 28.61 ÷ 1.00 = 28.6

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-ready27.8/100×0.30 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) × 7 (quality) × 1.0 (full) = 14.0 of 20 max

  • [probe] https://support.claude.com/llms.txtPROBE llms.txt: HTTP 200 at https://support.claude.com/llms.txt # Claude Help Center > Search for answers or browse by topic ## English ### Claude - [Release notes](https://support
  • [claimed-docs] https://support.claude.com/en/articles/11817273-use-claude-s-chat-search-and-memory-to-build-on-previous-context.mdYou can prompt Claude to search through your previous conversations to find and reference relevant information in new chats.
  • [claimed-docs] https://support.claude.com/en/articles/11817273-use-claude-s-chat-search-and-memory-to-build-on-previous-context.mdThis article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how to turn these features on or off.
  • [probe] https://support.claude.com/en/.mdPROBE docs-md: HTTP 404 at https://support.claude.com/en/.md

Run the product headlessly / in CI for automationweight 2

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

  • [claimed-docs] https://support.claude.com/en/articles/12012173-get-started-with-claude-in-chrome.mdBuild with Claude Code in your terminal, then deploy to a URL Claude can reach
  • [claimed-docs] https://support.claude.com/en/articles/15924927-use-claude-code-cli-with-a-screen-reader.mdThe screen reader mode brings Claude Code back to the basic terminal experience: plain, sequential text with added labels and cues
  • [community] https://news.ycombinator.com/item?id=47584540src/cli/print.ts is the single worst function in the codebase by every metric: 3,167 lines long, 12 levels of nesting at its deepest, ~486 branch points of cyclomatic complexity... This should be at minimum 8–10 separate modules.

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

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

  • [claimed-docs] https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp.mdBuild your own remote MCP servers to connect with any tool.
  • [claimed-docs] https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp.mdYou can: Connect Claude to existing remote MCP servers. Build your own remote MCP servers to connect with any tool.
  • [claimed-docs] https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp.mdYou can: - Connect Claude to existing remote MCP servers. - Build your own remote MCP servers to connect with any tool.
  • [claimed-docs] https://support.claude.com/en/articles/10949351-getting-started-with-local-mcp-servers-on-claude-desktop.mdinstalling and managing local MCP servers has become significantly easier... install local MCP servers on your computer as easily as browser extensions
  • [claimed-docs] https://support.claude.com/en/articles/10949351-getting-started-with-local-mcp-servers-on-claude-desktop.mdyou can now install local MCP servers on your computer as easily as browser extensions
  • [claimed-docs] https://support.claude.com/en/articles/14328846-browse-skills-connectors-and-plugins-in-one-directory.mdOur unified directory brings skills, connectors, and plugins together in one place so you can find and install everything that customizes Claude
  • [probe] https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcpofficial MCP server documented at https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp

Connect an agent via an official MCP serverweight 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

Use an official CLIweight 2

2 (weight) × 6 (quality) × 0.3 (disputed) = 3.6 of 20 max

  • [claimed-docs] https://support.claude.com/en/articles/12012173-get-started-with-claude-in-chrome.mdBuild with Claude Code in your terminal, then deploy to a URL Claude can reach. Test and verify in the browser with the Chrome extension. Debug issues using console logs
  • [claimed-docs] https://support.claude.com/en/articles/12012173-get-started-with-claude-in-chrome.mdBuild with Claude Code in your terminal, then deploy to a URL Claude can reach. Test and verify in the browser with the Chrome extension.
  • [claimed-docs] https://support.claude.com/en/articles/12012173-get-started-with-claude-in-chrome.mdBuild with Claude Code in your terminal, then deploy to a URL Claude can reach
  • [claimed-docs] https://support.claude.com/en/articles/15924927-use-claude-code-cli-with-a-screen-reader.mdIt was built with and for screen reader users, and it's useful to anyone who wants plain output for braille displays, slow connections, or transcripts.
  • [community] https://news.ycombinator.com/item?id=43163011Tried claude code, and have an empty unresponsive terminal. Looks cool in the demo though, but not sure this is going to perform better than Cursor, and shipping this as an interactive CLI instead of an extension is... a choice
  • [community] https://news.ycombinator.com/item?id=47584540src/cli/print.ts is the single worst function in the codebase by every metric: 3,167 lines long, 12 levels of nesting at its deepest, ~486 branch points of cyclomatic complexity... This should be at minimum 8–10 separate modules.

Drive the product through a documented public APIweight 3

3 (weight) × 3 (quality) × 0.6 (partial) = 5.4 of 30 max

  • [claimed-docs] https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan.mdAudit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude usage data including activity logs, chat histories, and file content
  • [claimed-docs] https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan.mdAudit logs: capture key information about user actions, system events, and data access.
  • [claimed-docs] https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan.mdEnterprise includes everything in the Team plan, plus the following: - Security features to ensure the safety and compliance of your organization’s data including: - Audit logs: capture key information about user actions, system events, and data access.
  • [claimed-docs] https://support.claude.com/en/articles/8114533-i-ve-been-using-other-large-language-models-llms-to-power-my-product-how-should-i-alter-my-prompts-when-switching-to-claude.mdYou can use the prompt improver in the Claude Console to automatically adapt prompts that were originally written for other AI models.
  • [probe] https://support.claude.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.claude.com/api/openapi.json, https://support.claude.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

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

Build against official SDKsweight 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

Subscribe to events via webhooksweight 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

Agent-ready = 50.0 ÷ 180 × 100 = 27.8

API quality0.0/100×0.20 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) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://support.claude.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.claude.com/api/openapi.json, https://support.claude.com/.well-known/openapi.json)
  • [probe] https://support.claude.com/en/.mdPROBE docs-md: HTTP 404 at https://support.claude.com/en/.md

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://support.claude.com/openapi.jsonPROBE openapi: all candidate paths 404 (https://support.claude.com/openapi.json, https://support.claude.com/swagger.json, https://support.claude.com/api/openapi.json, https://support.claude.com/.well-known/openapi.json)
  • [probe] https://support.claude.com/en/.mdPROBE docs-md: HTTP 404 at https://support.claude.com/en/.md

Test against a sandbox environment without touching production dataweight 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

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 = 0.0 ÷ 70 × 100 = 0.0

Openness15.4/100×0.20 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) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdWith Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized research, and more.
  • [claimed-docs] https://support.claude.com/en/articles/11101966-use-voice-mode.mdVoice mode allows you to have complete spoken conversations with Claude.
  • [claimed-docs] https://support.claude.com/en/articles/16607400-use-the-built-in-browser-in-claude-cowork.mdClaude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.
  • [claimed-docs] https://support.claude.com/en/articles/14128542-let-claude-use-your-computer-in-cowork.mdit may navigate to your screen directly—clicking, typing, and opening apps just like you would.
  • [claimed-docs] https://support.claude.com/en/articles/9797531-what-is-the-enterprise-plan.mdAudit logs: capture key information about user actions, system events, and data access. ... Compliance API: programmatically access Claude usage data including activity logs, chat histories, and file content
  • [claimed-docs] https://support.claude.com/en/articles/9517075-what-are-projects.mdProjects allow you to create self-contained workspaces with their own chat histories and knowledge bases.
  • [claimed-docs] https://support.claude.com/en/articles/11817273-use-claude-s-chat-search-and-memory-to-build-on-previous-context.mdThis article explains how chat search and memory work, what Claude does and doesn’t remember, how to review and edit what’s saved, and how to turn these features on or off.

Export all of my data in open formats and leaveweight 3

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

  • [claimed-docs] https://support.claude.com/en/articles/9450526-export-your-claude-data.mdIndividual Claude users can export user information and chat history from Settings > Privacy
  • [claimed-docs] https://support.claude.com/en/articles/9450526-export-your-claude-data.mdData exports include conversation data and the user data for your account.

Read the product's source under an open licenseweight 2

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

  • [community] https://news.ycombinator.com/item?id=48734373Codex CLI is FOSS, unlike Claude Code, so Codex is less likely to do things like that, and it's one more reason to avoid Claude Code and Claude in general.

Self-host the core 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

Openness = 10.8 ÷ 70 × 100 = 15.4

Built-in AI85.6/100×0.15 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) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

  • [claimed-docs] https://support.claude.com/en/articles/8241126-upload-files-to-claude.mdClaude can work with the following document types: - PDF - DOCX - CSV - TXT - HTML - ODT - RTF - EPUB - JSON - XLSX
  • [claimed-docs] https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude.mdPrompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can download and use immediately.
  • [claimed-docs] https://support.claude.com/en/articles/9517075-what-are-projects.mdProjects allow you to create self-contained workspaces with their own chat histories and knowledge bases.
  • [claimed-docs] https://support.claude.com/en/articles/11088861-use-research-on-claude.mdWith research, Claude delivers thorough answers in minutes, complete with easy-to-check citations so you can trust Claude's findings.
  • [claimed-docs] https://support.claude.com/en/articles/11088861-use-research-on-claude.mdResearch transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.
  • [claimed-docs] https://support.claude.com/en/articles/11088861-use-research-on-claude.mdClaude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.
  • [claimed-docs] https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude.mdproduce reports with charts and visualizations, and generate presentations from your documents—all without specialized software skills
  • [claimed-docs] https://support.claude.com/en/articles/10166901-use-google-workspace-connectors.mdConnect your Gmail, Google Calendar, and Google Drive to Claude so you can search and send emails, manage your calendar, work with documents, and save files—all without leaving the conversation.
  • [claimed-docs] https://support.claude.com/en/articles/8241126-upload-files-to-claude.mdFiles can be uploaded to individual chats or uploaded to a project's Files section for persistent reference across conversations.

Set up automations that run autonomously in the backgroundweight 2

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

  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdInstead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time.
  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdScheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.
  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdyou describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time
  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdWith Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized research, and more.
  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdClaude can take on complex, multi-step tasks and execute them on your behalf.
  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdbrings Claude Code's agentic capabilities to knowledge work beyond coding

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

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

  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdWith Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized research, and more.
  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdInstead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time.
  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdClaude can take on complex, multi-step tasks and execute them on your behalf.
  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdScheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.
  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdbrings Claude Code's agentic capabilities to knowledge work beyond coding
  • [claimed-docs] https://support.claude.com/en/articles/11088861-use-research-on-claude.mdResearch transforms how Claude finds and analyzes information. Claude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.
  • [claimed-docs] https://support.claude.com/en/articles/11088861-use-research-on-claude.mdClaude operates agentically, conducting multiple searches that build on each other while determining exactly what to investigate next.

Operate the product with natural-language commandsweight 2

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

  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdWith Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized research, and more.
  • [claimed-docs] https://support.claude.com/en/articles/16607400-use-the-built-in-browser-in-claude-cowork.mdClaude opens sites, reads pages, clicks, types, and fills forms while you watch, with no need to switch windows.
  • [claimed-docs] https://support.claude.com/en/articles/14128542-let-claude-use-your-computer-in-cowork.mdit may navigate to your screen directly—clicking, typing, and opening apps just like you would.
  • [claimed-docs] https://support.claude.com/en/articles/12111783-create-and-edit-files-with-claude.mdPrompt Claude using natural language to generate Excel spreadsheets, PowerPoint presentations, Word documents, and PDF files that you can download and use immediately.
  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdClaude can take on complex, multi-step tasks and execute them on your behalf.
  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdScheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.
  • [claimed-docs] https://support.claude.com/en/articles/9487310-what-are-artifacts-and-how-do-i-use-them.mdbuild tools, visualizations, and experiences by simply describing what you need
  • [community] https://news.ycombinator.com/item?id=48463808I've been running Opus 4.8 for agentic coding and I don't see it being significantly better than Sonnet 4.5. I find that pairing Google Gemini and Claude (having Gemini review Claude's code) seems to yield better results.
  • [community] https://news.ycombinator.com/item?id=46902223Anecdotal, but it 1 shot fixed a UI bug that neither Opus 4.5/Codex 5.2-high could fix.
  • [community] https://news.ycombinator.com/item?id=43163011Claude is significantly better than other models at code assistant tasks, or at least in the way I use it.

Built-in AI = 77.0 ÷ 90 × 100 = 85.6

Automation29.0/100×0.15 of the PA blend

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

Perform bulk operations across many items at onceweight 2

2 (weight) × 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) × 4 (quality) × 0.6 (partial) = 7.2 of 30 max

  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdScheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.
  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdyou describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time
  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdInstead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time.
  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdClaude can take on complex, multi-step tasks and execute them on your behalf.

Schedule recurring jobs or workflowsweight 2

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

  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdInstead of starting each task from scratch, you describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time.
  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdScheduled tasks allow you to delegate work to Claude Cowork by creating tasks that run automatically on a recurring basis, or on demand.
  • [claimed-docs] https://support.claude.com/en/articles/13854387-schedule-recurring-tasks-in-claude-cowork.mdyou describe it once and Claude handles it on your schedule—delivering finished outputs like reports, briefings, and summaries every time
  • [claimed-docs] https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork.mdWith Cowork, you can describe an outcome, step away, and come back to finished work—formatted documents, organized files, synthesized research, and more.

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 = 23.2 ÷ 80 × 100 = 29.0