Skip to content
ProductArena

How cubic’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 36.2 × 0.30 = 10.86

API quality 0.0 × 0.20 = 0.00

Openness 6.0 × 0.20 = 1.20

Built-in AI 76.7 × 0.15 = 11.51

Automation 28.0 × 0.15 = 4.20

(10.86 + 0.00 + 1.20 + 11.51 + 4.20) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 27.77 ÷ 1.00 = 27.8

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-ready36.2/100×0.30 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://docs.cubic.dev/llms.txt“PROBE llms.txt: HTTP 200 at https://docs.cubic.dev/llms.txt # cubic documentation > cubic reviews code on GitHub and in local coding workflows. These docs cover review setup, codi”
  • [probe] https://docs.cubic.dev/ai-review/introduction.md“PROBE docs-md: HTTP 200 at https://docs.cubic.dev/ai-review/introduction.md > ## Documentation Index > Fetch the complete documentation index at: https://docs.cubic.dev/llms.txt > Use this file to”

Run the product headlessly / in CI for automationweight 2

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

  • [claimed-docs] https://docs.cubic.dev/ai-review/introduction“Once installed, cubic automatically reviews new pull requests.”
  • [claimed-docs] https://docs.cubic.dev/ide/cli-review“The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
  • [probe] https://docs.cubic.dev/ide/cli-review“official CLI documented at https://docs.cubic.dev/ide/cli-review”
  • [claimed-docs] https://docs.cubic.dev/ai-review/key-features.md“The AI automatically scans every pull request for a wide range of issues, including logic errors, style inconsistencies, and potential security vulnerabilities.”
  • [claimed-docs] https://docs.cubic.dev/codebase-scan/codebase-scans“Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”

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

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

  • [claimed-docs] https://docs.cubic.dev/ide/agent-setup“Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase scan issues.”
  • [probe] https://docs.cubic.dev/ide/mcp-server“official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
  • [claimed-docs] https://www.cubic.dev/pricing-plans“Connect to Jira, Linear, Asana, and Notion”
  • [claimed-docs] https://docs.cubic.dev/integrations/notion-integration.md“Add page context from Notion to make AI reviews understand your requirements and generate accurate PR descriptions.”

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.cubic.dev/ide/agent-setup“Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase scan issues.”
  • [claimed-docs] https://docs.cubic.dev/changelog/changelog“You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving your MCP client.”
  • [claimed-docs] https://docs.cubic.dev/ide/agent-setup.md“Install and connect cubic in Cursor, Claude Code, VS Code, Codex, Gemini CLI, or another coding tool.”
  • [probe] https://docs.cubic.dev/ide/mcp-server“official MCP server documented at https://docs.cubic.dev/ide/mcp-server”

Use an official CLIweight 2

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

  • [claimed-docs] https://docs.cubic.dev/ide/cli-review“The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
  • [probe] https://docs.cubic.dev/ide/cli-review“official CLI documented at https://docs.cubic.dev/ide/cli-review”

Drive the product through a documented public APIweight 3

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

  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
  • [claimed-docs] https://docs.cubic.dev/ide/agent-setup“Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase scan issues.”
  • [probe] https://docs.cubic.dev/ide/mcp-server“official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
  • [probe] https://docs.cubic.dev/ide/cli-review“official CLI documented at https://docs.cubic.dev/ide/cli-review”
  • [probe] https://docs.cubic.dev/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api/openapi.json, https://docs.cubic.dev/.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.cubic.dev/account/roles-and-permissions.md“cubic uses a role-based access control system to manage who can make changes to your team's subscription and settings. Every team member has one of three roles”
  • [claimed-docs] https://docs.cubic.dev/ide/agent-setup“Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase scan issues.”
  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

Build against official SDKsweight 2

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

  • [probe] https://docs.cubic.dev/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api/openapi.json, https://docs.cubic.dev/.well-known/openapi.json)”
  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
  • [probe] https://docs.cubic.dev/ide/mcp-server“official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
  • [probe] https://docs.cubic.dev/ide/cli-review“official CLI documented at https://docs.cubic.dev/ide/cli-review”

Subscribe to events via webhooksweight 2

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

  • [probe] https://docs.cubic.dev/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api/openapi.json, https://docs.cubic.dev/.well-known/openapi.json)”
  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

Agent-ready = 76.0 ÷ 210 × 100 = 36.2

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://docs.cubic.dev/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api/openapi.json, https://docs.cubic.dev/.well-known/openapi.json)”
  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

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.cubic.dev/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api/openapi.json, https://docs.cubic.dev/.well-known/openapi.json)”
  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”

Test against a sandbox environment without touching production dataweight 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

Rely on versioned APIs with a documented deprecation policyweight 2

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

  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
  • [probe] https://docs.cubic.dev/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api/openapi.json, https://docs.cubic.dev/.well-known/openapi.json)”

API quality = 0.0 ÷ 60 × 100 = 0.0

Openness6.0/100×0.20 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) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
  • [claimed-docs] https://docs.cubic.dev/ide/agent-setup“Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase scan issues.”
  • [claimed-docs] https://docs.cubic.dev/changelog/changelog“You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving your MCP client.”
  • [claimed-docs] https://docs.cubic.dev/ide/cli-review“The **cubic CLI** reviews local changes before you push. It finds bugs and generates a prompt that your coding agent can use to fix them.”
  • [probe] https://docs.cubic.dev/openapi.json“PROBE openapi: all candidate paths 404 (https://docs.cubic.dev/openapi.json, https://docs.cubic.dev/swagger.json, https://docs.cubic.dev/api/openapi.json, https://docs.cubic.dev/.well-known/openapi.json)”
  • [probe] https://docs.cubic.dev/ide/mcp-server“official MCP server documented at https://docs.cubic.dev/ide/mcp-server”
  • [probe] https://docs.cubic.dev/ide/cli-review“official CLI documented at https://docs.cubic.dev/ide/cli-review”

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.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
  • [claimed-docs] https://docs.cubic.dev/wiki/ai-wiki“cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams, and more.”

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

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

Openness = 6.0 ÷ 100 × 100 = 6.0

Built-in AI76.7/100×0.15 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) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

  • [claimed-docs] https://docs.cubic.dev/ai-review/introduction“Spots bugs and improvements: Comments on bugs and improvements in pull requests”
  • [claimed-docs] https://docs.cubic.dev/ai-review/introduction“PR summaries: Generates PR descriptions based on code changes”
  • [claimed-docs] https://docs.cubic.dev/wiki/ai-wiki“cubic's AI wiki automatically indexes your codebase and produces searchable wikis, complete with links to source code, architecture diagrams, and more.”
  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/issue-analysis.md“cubic can automatically analyze your pull requests to see if they meet the requirements from your linked Linear or Jira issues.”
  • [claimed-docs] https://docs.cubic.dev/analytics/overview.md“The analytics dashboard shows how your team ships code across three lenses: AI coding usage, AI review impact, and delivery speed.”
  • [community] https://hn.algolia.com/api/v1/items/46605224“I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanations than just basic checks; for example, compared to using a regular GPT or Claude. I may not be an experienced developer, but I can confidently say that your Cubic.dev is really powerful.”

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://docs.cubic.dev/ai-review/introduction“Once installed, cubic automatically reviews new pull requests.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart“cubic generates the fix and pushes it to your PR branch.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart“Enable [auto-approval](/ai-review/auto-approval) to let cubic approve PRs that meet your review policy.”
  • [claimed-docs] https://docs.cubic.dev/codebase-scan/codebase-scans“Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart.md“Enable auto-approval to let cubic approve PRs that meet your review policy.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/key-features.md“cubic can automatically fix issues in the background. When the AI spots a problem, you can click the **Fix with cubic** button”
  • [claimed-docs] https://docs.cubic.dev/ai-review/auto-approval.md“Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/memory-and-learning“cubic automatically learns when you: Reply to its comments... React to suggestions: Thumbs up/down help cubic calibrate what's useful vs noise”

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

3 (weight) × 7 (quality) × 1.0 (full) = 21.0 of 30 max

  • [claimed-docs] https://docs.cubic.dev/ai-review/introduction“To review a PR that was opened _before_ you installed the app, comment: `@cubic-dev-ai review this PR`.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/key-features“Ultrareview runs a longer review using cubic's most capable review models, which is useful for risky migrations, security-sensitive changes, or complex refactors.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart“cubic generates the fix and pushes it to your PR branch.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart“Reply to a review comment to ask for clarification:”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart“Enable [auto-approval](/ai-review/auto-approval) to let cubic approve PRs that meet your review policy.”
  • [claimed-docs] https://docs.cubic.dev/codebase-scan/codebase-scans“Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
  • [community] https://hn.algolia.com/api/v1/items/46605224“I really liked it - it hit the mark. The current balance works very well, and it genuinely surprised me. It provides more technical explanations than just basic checks; for example, compared to using a regular GPT or Claude. I may not be an experienced developer, but I can confidently say that your Cubic.dev is really powerful.”

Operate the product with natural-language commandsweight 2

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

  • [claimed-docs] https://docs.cubic.dev/ai-review/introduction“To review a PR that was opened _before_ you installed the app, comment: `@cubic-dev-ai review this PR`.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart“Reply to a review comment to ask for clarification:”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart“@cubic-dev-ai review this PR”
  • [claimed-docs] https://docs.cubic.dev/ai-review/interactive-comments.md“Interact with cubic in PR comments to ask questions, trigger reviews, and fix issues. You can tag `@cubic-dev-ai` directly, or reply to cubic's existing comments to continue the conversation.”
  • [claimed-docs] https://docs.cubic.dev/ide/agent-setup“Connect cubic's MCP server to your coding agent to read review findings and codebase context, request PR reviews, and triage PR or codebase scan issues.”
  • [claimed-docs] https://docs.cubic.dev/changelog/changelog“You can now ask your coding agent to check your cubic subscription, manage team seats and roles, and purchase more seats without leaving your MCP client.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/key-features“When a pull request needs extra scrutiny, you can ask cubic for an Ultrareview.”

Built-in AI = 69.0 ÷ 90 × 100 = 76.7

Automation28.0/100×0.15 of the PA blend

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

Perform bulk operations across many items at onceweight 2

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

  • [claimed-docs] https://docs.cubic.dev/codebase-scan/codebase-scans“Codebase scans deploy thousands of AI agents to find bugs and vulnerabilities across your repository.”
  • [claimed-docs] https://docs.cubic.dev/analytics/api“The Analytics API gives you PR-level data on how many issues were flagged, how many were fixed, how much AI code was authored, etc.”
  • [claimed-docs] https://docs.cubic.dev/analytics/overview.md“The analytics dashboard shows how your team ships code across three lenses: AI coding usage, AI review impact, and delivery speed.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/cross-repo-reviews.md“Cross-repo reviews help cubic catch changes that need a matching update in another repository. Link related repositories so reviews can check shared APIs, schemas, docs, or release work.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart“Enable [auto-approval](/ai-review/auto-approval) to let cubic approve PRs that meet your review policy.”

Define rules that trigger actions automatically on eventsweight 3

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

  • [claimed-docs] https://docs.cubic.dev/ai-review/introduction“Once installed, cubic automatically reviews new pull requests.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/custom-agents“Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart“Enable [auto-approval](/ai-review/auto-approval) to let cubic approve PRs that meet your review policy.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/quickstart.md“Enable auto-approval to let cubic approve PRs that meet your review policy.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/key-features.md“cubic can automatically fix issues in the background. When the AI spots a problem, you can click the **Fix with cubic** button”
  • [claimed-docs] https://docs.cubic.dev/configure/cubic-yaml“cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, and custom agents.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/auto-approval.md“Auto-approval lets you skip human review for pull requests that cubic determines are low risk and issue-free.”
  • [community] https://hn.algolia.com/api/v1/items/45901525“The 'in-codebase' approach is the right one, but a YAML file with plain text is a half-measure. The most reliable rule that 'lives next to the code' is an architectural test... a more robust engineering solution, unlike semantic text interpretation, which can fail.”

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

1 (weight) × 3 (quality) × 0.6 (partial) = 1.8 of 10 max

  • [claimed-docs] https://docs.cubic.dev/configure/cubic-yaml“`cubic.yaml` lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, and custom agents.”
  • [claimed-docs] https://docs.cubic.dev/configure/cubic-yaml“cubic.yaml lives in the root of your repository and becomes the source of truth for AI review behavior, ignore patterns, PR descriptions, and custom agents.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/custom-agents“Custom agents are review rules that enforce your organization's specific best practices across pull requests.”
  • [claimed-docs] https://docs.cubic.dev/ai-review/introduction.md“Custom agents: Enforce your team's coding standards”

Automation = 16.8 ÷ 60 × 100 = 28.0