Skip to content
ProductArena

How Undermind’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 Score16/100

Agent-ready 16.9 × 0.30 = 5.07

API quality 0.0 × 0.20 = 0.00

Openness 12.0 × 0.20 = 2.40

Built-in AI 39.6 × 0.15 = 5.94

Automation 18.0 × 0.15 = 2.70

(5.07 + 0.00 + 2.40 + 5.94 + 2.70) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 16.11 ÷ 1.00 = 16.1

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-ready16.9/100×0.30 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) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://undermind.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
  • [probe] https://undermind.ai/mcp.md“PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.well-known/openapi.json)”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 2 (quality) × 0.6 (partial) = 2.4 of 20 max

  • [claimed-docs] https://undermind.ai/enterprise“Integrate Undermind's deep literature research capabilities directly into your other tools and workflows.”
  • [claimed-docs] https://undermind.ai/enterprise“Programmatic queries via API”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.well-known/openapi.json)”

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://undermind.ai/mcp“This adds Undermind directly to Cursor”
  • [claimed-docs] https://undermind.ai/mcp“Undermind works with any MCP-compatible client. The protocol's recommended way for a new client to identify itself is a Client ID Metadata Document (CIMD).”
  • [claimed-docs] https://undermind.ai/mcp“This adds Undermind to VS Code as an MCP server.”
  • [claimed-docs] https://undermind.ai/mcp“claude mcp add --transport http undermind https://mcp.undermind.ai/mcp”
  • [claimed-docs] https://undermind.ai/mcp“Undermind works with any MCP-compatible client.”
  • [claimed-docs] https://undermind.ai/mcp“Undermind is available as a published ChatGPT app.”

Connect an agent via an official MCP serverweight 3

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

  • [claimed-docs] https://undermind.ai/mcp“This adds Undermind directly to Cursor”
  • [claimed-docs] https://undermind.ai/mcp“Undermind works with any MCP-compatible client. The protocol's recommended way for a new client to identify itself is a Client ID Metadata Document (CIMD).”
  • [claimed-docs] https://undermind.ai/mcp“This adds Undermind to VS Code as an MCP server.”
  • [claimed-docs] https://undermind.ai/mcp“claude mcp add --transport http undermind https://mcp.undermind.ai/mcp”
  • [claimed-docs] https://undermind.ai/mcp“Point the client at `https://mcp.undermind.ai/mcp`”
  • [claimed-docs] https://undermind.ai/mcp“Undermind works with any MCP-compatible client.”
  • [probe] https://undermind.ai/mcp“official MCP server documented at https://undermind.ai/mcp”

Use an official CLIweight 2

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

  • [claimed-docs] https://undermind.ai/mcp“claude mcp add --transport http undermind https://mcp.undermind.ai/mcp”
  • [probe] https://undermind.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
  • [probe] https://undermind.ai/mcp.md“PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.well-known/openapi.json)”

Drive the product through a documented public APIweight 3

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

  • [claimed-docs] https://undermind.ai/mcp“Undermind works with any MCP-compatible client. The protocol's recommended way for a new client to identify itself is a Client ID Metadata Document (CIMD).”
  • [claimed-docs] https://undermind.ai/mcp“Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own searches, follows citations and key authors, and stops only when new searches stop finding relevant papers.”
  • [claimed-docs] https://undermind.ai/mcp“This adds Undermind to VS Code as an MCP server.”
  • [claimed-docs] https://undermind.ai/mcp“claude mcp add --transport http undermind https://mcp.undermind.ai/mcp”
  • [claimed-docs] https://undermind.ai/mcp“Point the client at `https://mcp.undermind.ai/mcp`”
  • [claimed-docs] https://undermind.ai/enterprise“Programmatic queries via API”
  • [probe] https://undermind.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
  • [probe] https://undermind.ai/mcp.md“PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.well-known/openapi.json)”
  • [probe] https://undermind.ai/mcp“official MCP server documented at https://undermind.ai/mcp”

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://undermind.ai/enterprise“Programmatic queries via API”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.well-known/openapi.json)”

Build against official SDKsweight 2

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

  • [claimed-docs] https://undermind.ai/enterprise“Programmatic queries via API”
  • [probe] https://undermind.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
  • [probe] https://undermind.ai/mcp.md“PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.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://undermind.ai“Get notified whenever relevant papers are published.”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.well-known/openapi.json)”

Agent-ready = 35.4 ÷ 210 × 100 = 16.9

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://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.well-known/openapi.json)”
  • [probe] https://undermind.ai/mcp.md“PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
  • [probe] https://undermind.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
  • [claimed-docs] https://undermind.ai/enterprise“Programmatic queries via API”

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

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

  • [claimed-docs] https://undermind.ai/enterprise“Programmatic queries via API”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.well-known/openapi.json)”
  • [probe] https://undermind.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
  • [probe] https://undermind.ai/mcp.md“PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”

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://undermind.ai/enterprise“Programmatic queries via API”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.well-known/openapi.json)”

API quality = 0.0 ÷ 60 × 100 = 0.0

Openness12.0/100×0.20 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://undermind.ai/mcp“Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own searches, follows citations and key authors, and stops only when new searches stop finding relevant papers.”
  • [claimed-docs] https://undermind.ai/mcp“Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
  • [claimed-docs] https://undermind.ai/mcp“Creates and edits Markdown notes, syntheses, and reports in the workspace. Citations link back to the source papers, and files stay available to agents across sessions.”
  • [claimed-docs] https://undermind.ai/mcp“Curate papers into a folder for long-term use.”
  • [claimed-docs] https://undermind.ai/mcp“Star important papers across the workspace.”
  • [claimed-docs] https://undermind.ai/enterprise“Programmatic queries via API”
  • [claimed-docs] https://undermind.ai“Get notified whenever relevant papers are published.”
  • [probe] https://undermind.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://undermind.ai/llms.txt”
  • [probe] https://undermind.ai/mcp.md“PROBE docs-md: HTTP 404 at https://undermind.ai/mcp.md”
  • [probe] https://undermind.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://undermind.ai/openapi.json, https://undermind.ai/swagger.json, https://undermind.ai/api/openapi.json, https://undermind.ai/.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

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

Read the product's source under an open licenseweight 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

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 = 6.0 ÷ 50 × 100 = 12.0

Built-in AI39.6/100×0.15 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://undermind.ai/mcp“Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own searches, follows citations and key authors, and stops only when new searches stop finding relevant papers.”
  • [claimed-docs] https://undermind.ai/mcp“Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
  • [claimed-docs] https://undermind.ai/mcp“Creates and edits Markdown notes, syntheses, and reports in the workspace. Citations link back to the source papers, and files stay available to agents across sessions.”
  • [claimed-docs] https://undermind.ai“Get notified whenever relevant papers are published.”
  • [claimed-docs] https://undermind.ai“Trace any statement by following in-line citations back to the source paper”
  • [community] https://news.ycombinator.com/item?id=39906683“I actually was able to find at least 4 new informative papers... in less than six minutes, your search engine was able to give me more relevant search results than probably a week of searching Science Direct.”
  • [community] https://news.ycombinator.com/item?id=39906683“These are the best results that I've gotten from an AI research assistant. I really don't mind the long latency... The 'Discovery Progress and Exhaustiveness' section is a bit confusing as a user.”

Set up automations that run autonomously in the backgroundweight 2

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

  • [claimed-docs] https://undermind.ai“Get notified whenever relevant papers are published.”

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

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

  • [claimed-docs] https://undermind.ai/mcp“This adds Undermind directly to Cursor”
  • [claimed-docs] https://undermind.ai/mcp“Undermind works with any MCP-compatible client. The protocol's recommended way for a new client to identify itself is a Client ID Metadata Document (CIMD).”
  • [claimed-docs] https://undermind.ai/mcp“Undermind is available as a published ChatGPT app.”

Operate the product with natural-language commandsweight 2

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

  • [claimed-docs] https://undermind.ai/mcp“Undermind works with any MCP-compatible client. The protocol's recommended way for a new client to identify itself is a Client ID Metadata Document (CIMD).”
  • [claimed-docs] https://undermind.ai/mcp“Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own searches, follows citations and key authors, and stops only when new searches stop finding relevant papers.”
  • [claimed-docs] https://undermind.ai/mcp“This adds Undermind to VS Code as an MCP server.”
  • [claimed-docs] https://undermind.ai/mcp“claude mcp add --transport http undermind https://mcp.undermind.ai/mcp”
  • [claimed-docs] https://undermind.ai/mcp“Undermind is available as a published ChatGPT app.”
  • [probe] https://undermind.ai/mcp“official MCP server documented at https://undermind.ai/mcp”

Built-in AI = 35.6 ÷ 90 × 100 = 39.6

Automation18.0/100×0.15 of the PA blend

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

Perform bulk operations across many items at onceweight 2

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

  • [claimed-docs] https://undermind.ai/mcp“Reads full-text PDFs in parallel and answers specific questions across many papers at once, including from figures, tables, and equations.”
  • [claimed-docs] https://undermind.ai/mcp“Runs a deep literature review from an open-ended research goal and produces a ranked list of papers with a written synthesis. Plans its own searches, follows citations and key authors, and stops only when new searches stop finding relevant papers.”
  • [claimed-docs] https://undermind.ai/enterprise“Programmatic queries via API”
  • [claimed-docs] https://undermind.ai/mcp“Curate papers into a folder for long-term use.”
  • [claimed-docs] https://undermind.ai/mcp“Star important papers across the workspace.”

Define rules that trigger actions automatically on eventsweight 3

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

  • [claimed-docs] https://undermind.ai“Get notified whenever relevant papers are published.”

Schedule recurring jobs or workflowsweight 2

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

  • [claimed-docs] https://undermind.ai“Get notified whenever relevant papers are published.”

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 = 12.6 ÷ 70 × 100 = 18.0