Skip to content
ProductArena

How Sakana Marlin’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 Score9/100

Agent-ready 0.0 × 0.30 = 0.00

API quality 0.0 × 0.20 = 0.00

Openness 0.0 × 0.20 = 0.00

Built-in AI 59.1 × 0.15 = 8.87

Automation 0.0 × 0.15 = 0.00

(0.00 + 0.00 + 0.00 + 8.87 + 0.00) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 8.87 ÷ 1.00 = 8.9

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-ready0.0/100×0.30 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://sakana.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://sakana.ai/llms.txt”
  • [probe] https://sakana.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://sakana.ai/openapi.json, https://sakana.ai/swagger.json, https://sakana.ai/api/openapi.json, https://sakana.ai/.well-known/openapi.json)”

Run the product headlessly / in CI for automationweight 2

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

  • [probe] https://sakana.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://sakana.ai/llms.txt”
  • [probe] https://sakana.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://sakana.ai/openapi.json, https://sakana.ai/swagger.json, https://sakana.ai/api/openapi.json, https://sakana.ai/.well-known/openapi.json)”
  • [claimed-docs] https://sakana.ai/marlin/“Add your card. Start right away.”

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

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

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

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

Drive the product through a documented public APIweight 3

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

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

Issue scoped/least-privilege API credentials for an agentweight 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

Build against official SDKsweight 2

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

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

Subscribe to events via webhooksweight 2

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

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

Agent-ready = 0.0 ÷ 130 × 100 = 0.0

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

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

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

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

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

API quality = 0.0 ÷ 40 × 100 = 0.0

Openness0.0/100×0.20 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) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

  • [probe] https://sakana.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://sakana.ai/llms.txt”
  • [probe] https://sakana.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://sakana.ai/openapi.json, https://sakana.ai/swagger.json, https://sakana.ai/api/openapi.json, https://sakana.ai/.well-known/openapi.json)”
  • [claimed-docs] https://sakana.ai/marlin/“Add your card. Start right away.”

Export all of my data in open formats and leaveweight 3

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

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

Read the product's source under an open licenseweight 2

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

  • [claimed-docs] https://sakana.ai/marlin-release/“We have made Marlin available as a pay-per-use tier to monthly Pro, Team, and Enterprise-tier plans.”
  • [probe] https://sakana.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://sakana.ai/llms.txt”
  • [probe] https://sakana.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://sakana.ai/openapi.json, https://sakana.ai/swagger.json, https://sakana.ai/api/openapi.json, https://sakana.ai/.well-known/openapi.json)”

Self-host the core productweight 3

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

  • [claimed-docs] https://sakana.ai/marlin-release/“We have made Marlin available as a pay-per-use tier to monthly Pro, Team, and Enterprise-tier plans.”
  • [claimed-docs] https://sakana.ai/marlin/“Add-on credits available (¥98 / credit)”
  • [claimed-docs] https://sakana.ai/marlin/“Add your card. Start right away.”

Openness = 0.0 ÷ 70 × 100 = 0.0

Built-in AI59.1/100×0.15 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://sakana.ai/marlin/“Sakana Marlin maps the causal relationships at work in complex business environments and organizes them into structured strategic options.”
  • [claimed-docs] https://sakana.ai/marlin/“It does more than summarize. Sakana Marlin maps the causal relationships at work in complex business environments and organizes them into structured strategic options.”
  • [claimed-docs] https://sakana.ai/marlin/“Rather than merely aggregating information, it compares and evaluates multiple hypotheses to provide deep insights.”
  • [claimed-docs] https://sakana.ai/marlin/“From ideation and data gathering to resolving contradictions and structuring the report, the AI autonomously executes the entire research process.”
  • [claimed-docs] https://sakana.ai/marlin/“The research was of extremely high quality, grounded strictly in primary sources, resulting in a highly convincing and reliable final report.”
  • [claimed-docs] https://sakana.ai/marlin-release/“Give it a research topic, and Marlin works autonomously for up to roughly eight hours, crafting a detailed strategy report up to a hundred pages long, along with executive summary slides.”

Set up automations that run autonomously in the backgroundweight 2

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

  • [claimed-docs] https://sakana.ai/marlin-release/“Give it a research topic, and Marlin works autonomously for up to roughly eight hours, crafting a detailed strategy report up to a hundred pages long, along with executive summary slides.”
  • [claimed-docs] https://sakana.ai/marlin-release/“Sakana Marlin sharpens the direction of the investigation through a brief exchange with the user. Once the course is set, it works without further human input”
  • [claimed-docs] https://sakana.ai/marlin/“From ideation and data gathering to resolving contradictions and structuring the report, the AI autonomously executes the entire research process.”
  • [claimed-docs] https://sakana.ai/marlin/“It is designed for use cases where you want to delegate everything up to "issue framing (agenda setting)" prior to decision-making to the AI.”

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

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

  • [claimed-docs] https://sakana.ai/marlin/“Once you set a research topic, it works without further human input: repeatedly forming hypotheses, gathering information, navigating the web, and resolving contradictions on its own.”
  • [claimed-docs] https://sakana.ai/marlin-release/“Give it a research topic, and Marlin works autonomously for up to roughly eight hours, crafting a detailed strategy report up to a hundred pages long, along with executive summary slides.”
  • [claimed-docs] https://sakana.ai/marlin-release/“Sakana Marlin sharpens the direction of the investigation through a brief exchange with the user. Once the course is set, it works without further human input”
  • [claimed-docs] https://sakana.ai/marlin/“From ideation and data gathering to resolving contradictions and structuring the report, the AI autonomously executes the entire research process.”
  • [claimed-docs] https://sakana.ai/marlin/“It is designed for use cases where you want to delegate everything up to "issue framing (agenda setting)" prior to decision-making to the AI.”

Operate the product with natural-language commandsweight 2

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

  • [claimed-docs] https://sakana.ai/marlin-release/“Sakana Marlin sharpens the direction of the investigation through a brief exchange with the user. Once the course is set, it works without further human input”
  • [claimed-docs] https://sakana.ai/marlin-release/“Give it a research topic, and Marlin works autonomously for up to roughly eight hours, crafting a detailed strategy report up to a hundred pages long, along with executive summary slides.”
  • [claimed-docs] https://sakana.ai/marlin/“It is designed for use cases where you want to delegate everything up to "issue framing (agenda setting)" prior to decision-making to the AI.”

Built-in AI = 53.2 ÷ 90 × 100 = 59.1

Automation0.0/100×0.15 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

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

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

  • [claimed-docs] https://sakana.ai/marlin-release/“Give it a research topic, and Marlin works autonomously for up to roughly eight hours, crafting a detailed strategy report up to a hundred pages long, along with executive summary slides.”
  • [claimed-docs] https://sakana.ai/marlin-release/“Sakana Marlin sharpens the direction of the investigation through a brief exchange with the user. Once the course is set, it works without further human input”
  • [probe] https://sakana.ai/llms.txt“PROBE llms.txt: HTTP 404 at https://sakana.ai/llms.txt”
  • [probe] https://sakana.ai/openapi.json“PROBE openapi: all candidate paths 404 (https://sakana.ai/openapi.json, https://sakana.ai/swagger.json, https://sakana.ai/api/openapi.json, https://sakana.ai/.well-known/openapi.json)”

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 = 0.0 ÷ 50 × 100 = 0.0