openai/evals
What happens to a stranger's pull request here, in the Porchlamp snapshot of 17 October 2026.
For openai/evals, the reply time has too small a sample to measure (0 pull requests counted; 10 needed). 100% of 111 outside pull requests got no reply within 14 days (20 April to 17 October 2026). It ranks 3,130 of 3,219 overall. It is not ranked for first-time contributors: this repository does not show a low enough barrier for a first-time contributor.
| Rank | 3,130 of 3,219 |
|---|---|
| Score | 29.26 |
| Tier | D |
| Median first reply | — |
| 14-day no-reply share | 100% |
| First-timer rank | This repository does not show a low enough barrier for a first-time contributor. |
| Ecosystem | Python |
| Window | 20 April to 17 October 2026 |
Composite
- Rank
- 3,130 of 3,219
- Score
- 29.26
- Tier
- D
- Coverage
- 75% · Ceiling B
- Quadrant
- Graveyard
Coordinates: leverage 29.8 (coverage 81%), friction 67.5 (coverage 67%)
Five pillars
| Pillar | Score | Coverage |
|---|---|---|
| Responsiveness | 15.7 | 60% |
| Criticality | 21.9 | 100% |
| Governance | 64.2 | 65% |
| Rigor | 20.0 | 60% |
| Accessibility | 26.8 | 85% |
The measured parameters
Responsiveness
| Parameter | Value | Score | Count | Window | Source |
|---|---|---|---|---|---|
| Decision Rate (90d)Share of outside pull requests that were merged or closed within 90 days. | 22.2% | 27.8 | 27 | 10 April to 9 July 2026 | primaryraw/pr_window/openai__evals.json |
| PR Ghost Rate (14d)Share of outside pull requests with no maintainer response, merge or close within 14 days. | 100.0% | 0.0 | 111 | 20 April to 17 October 2026 | primaryraw/pr_window/openai__evals.json |
| First-timer Merge RateShare of first-time outside authors' decided pull requests that were merged. | 10.0% | 12.5 | 20 | — | primaryraw/author_history/openai__evals.json |
| Time to First ResponseMedian hours from an outside pull request opening to its first substantive human reply. | Not shown: Insufficient sample size | ||||
| Time to Merge (p90)Hours within which 90% of merged outside pull requests were merged. | Not shown: Insufficient sample size | ||||
Criticality
| Parameter | Value | Score | Count | Window | Source |
|---|---|---|---|---|---|
| DependentsPackages in the registry that depend on this project, counted once each. | 1 | 34.4 | — | — | primaryraw/dependents/openai__evals.json |
| Monthly DownloadsDownloads from the package registry in a month. | 457 downloads a month | 7.6 | — | — | primaryraw/downloads/pypi__evals.json |
| OpenSSF CriticalityOpenSSF criticality score from 0 to 1, computed from the project's public activity signals. | 0.177 | 17.7 | — | — | primaryraw/github_meta/openai__evals.json |
Governance
| Parameter | Value | Score | Count | Window | Source |
|---|---|---|---|---|---|
| Elephant FactorThe fewest organisations that account for half of the last year's commits. | Not shown: Insufficient sample size | ||||
| Legal IP RegimeThe contributor licence regime: DCO, none, a foundation CLA or a corporate CLA. | No CLA or sign-off found | 85.0 | — | — | primaryraw/governance/openai__evals.json |
| Promotion LadderHow openly a contributor can become a maintainer, from closed to verified. | No written path to becoming a maintainer | 40.0 | — | — | primaryraw/governance/openai__evals.json |
Rigor
| Parameter | Value | Score | Count | Window | Source |
|---|---|---|---|---|---|
| AI Policy PostureWhether the project has a written policy on AI-assisted contributions. | No written AI policy | 40.0 | — | — | primaryraw/governance/openai__evals.json |
| Pipeline DefensesHow well the project's build and review pipeline defends against bad changes, 0 to 100. | Not shown: Insufficient sample size | ||||
| Substantive Review RateShare of decided pull requests that received a substantive review. | 0.0% | 0.0 | 17 | 10 April to 7 October 2026 | primaryraw/pr_window/openai__evals.json |
Accessibility
| Parameter | Value | Score | Count | Window | Source |
|---|---|---|---|---|---|
| Developer ExperienceDeveloper experience, 0 to 100: half CI run time, half setup signals. | 85 | 85.0 | 8 | — | primaryraw/actions_runs/openai__evals.json |
| Newcomer ConversionShare of first-time authors whose first pull request merged within 180 days. | 14.3% | 28.6 | 14 | — | primaryraw/author_history/openai__evals.json |
| Newcomer Issue SupplyOpen, unassigned, up-to-date issues marked for newcomers. | 0 | 0.0 | — | — | primaryraw/gfi/openai__evals.json |
| Newcomer Return RateShare of those merged first-time authors who sent a second pull request within 90 days. | Not shown: Insufficient sample size | ||||
Persona view
| Persona | Rank | Score | Tier | Status |
|---|---|---|---|---|
| Balanced | 3,130 of 3,219 | 29.26 | D | Rated |
| First-timer | This repository does not show a low enough barrier for a first-time contributor. | |||
| Career capital | This repository's production-criticality signal is not yet high enough for career-capital ranking. | |||
| Senior systems | 1,243 of 1,276 | 31.41 | D | Rated |
| AI-assisted | 3,650 of 3,696 | 26.83 | D | Rated |
Integrity
- Snapshot
- 2026-10-17
- Raw hash
- beba4da50aa98adbba15eb446919214bb86375bf86f845cfc3c2ce1554dc4549
No suspicion flags on this repository.
The full record is in data/2026-10-17/repos/73.json, under the key openai/evals.
How every number is measured: Porchlamp methodology.
Open an issue about this record and say what looks wrong.
Porchlamp (2026). openai/evals. Snapshot 2026-10-17. https://porchlamp.org/projects/openai/evals/. CC BY 4.0.
Similar projects
The ranked projects nearest this one in the same ecosystem.
- camel-ai/oasis (rank 3,116)
- Avaiga/taipy (rank 3,122)
- Guake/guake (rank 3,134)
- infobyte/faraday (rank 3,142)
- achael/eht-imaging (rank 3,146)