How Evals scored a B.

• code

  49/100
  • ✓ Contributors & bus-factor: 36 recent contributors
  • ✓ Commit recency: last commit 149d ago
  • ↓ Commit cadence: 0 commits in 90 days
  • ✓ Issue close ratio: 42% of issues closed
  • ↓ Release cadence: 0 releases in 12 months
  • ✓ Stars (log-damped): 19,426 stars (log-damped)
  • – Star authenticity: star-velocity check unavailable — GitHub no longer publishes stargazer timestamps for this repo
  • – Dependent repos: not measurable — no package listing on a registry we can query

• identity

  80/100
  • ✓ Organisation: Built by OpenAI · notable organisation (verified: Org profile shows a Verified badge stating the organization openai controls the domain openai.com; profile website https://openai.com/. No description or location field shown.)

• audits

  Not measured
  • – Third-party scans: no third-party scan data from listed registries

• freshness

  92/100
  • ↓ Last shipped: last commit 149d ago — standard-churn tools are expected to ship about every 120d

• community

  23/100
  • – Recommends: no recommends from gate-passing builders yet
  • ✓ Hacker News mentions: 1 Hacker News story pointing at this tool
  • – Signal depth: sparse data — this is an early reading from very few data points

Community did not lower this score. Community can only ever add. It did not raise the average for Evals, so the score shown is the one it would have without it. The component is still listed above, with its real value.

Components that could not be measured are left out of the average entirely, and their weight is redistributed, never scored as zero. Identity and Community are left out the same way when they would not have raised the score. How scores are calculated.