huggingface / evaluate
🤗 Evaluate: A library for easily evaluating machine learning models and datasets.
huggingface/evaluate holds a health index of 75 out of 100, placing it in the Good band. It scores highest on Community & Adoption (89/100) and lowest on Security (21/100). It was last updated 66 days ago. 3 contributors account for most of its recent work.
Software health index
Metrics are grouped into weighted categories on one standardized 1–100 scale. Overall starts as their weighted mean, calibrated against the distribution of the public record so bands carry percentile meaning; when public evidence triggers the High-Risk Jurisdiction Policy, the rating is adjusted and receives an At Risk ceiling of 34.
Score profile
Each axis is a category. The shape matters more than the average — a healthy subject fills the whole shape, while a spike-and-crater profile means strength in one dimension is masking risk in another.
The weighted overall 65 is calibrated to 75 on the published index scale (record calibration 2026-08-02).
Ownership
This repository is backed by an organization — shared, accountable stewardship that can outlive any single maintainer.
Package ecosystems
| Registry | Package | Version | Downloads / mo | Versions | Last publish | Tags |
|---|---|---|---|---|---|---|
| PyPI | evaluate | 0.4.6 | 3,670,360 | 14 | 357 days ago | metricsmachinelearningevaluateevaluation |
Metrics by category
Vitality
Is the project alive — is code being written and are releases shipping?
Development activity
How it's scored
| 18/36 | Push recency — last push 66 days ago |
| 4.2/36 | Commit cadence — 6/52 weeks with commits |
| 12.1/18 | Commit volume — 21 commits in the last year |
| 0/10 | OpenSSF Scorecard: Maintained — no data |
Inputs used
| commits_last_year | 21 |
| human_commit_share | 1 |
| days_since_last_push | 66 |
| active_weeks_last_year | 6 |
Release discipline
How it's scored
| 27/27 | Ships releases — 14 releases published |
| 16.2/36 | Release recency — latest release 357 days ago |
| 12.6/27 | Release cadence — a release every ~127.6 days |
| 0/10 | OpenSSF Scorecard: Signed-Releases — no data |
Inputs used
| releases_count | 14 |
| latest_release_tag | v0.4.6 |
| releases_from_tags | no |
| days_since_latest_release | 357 |
| mean_days_between_releases | 127.6 |
Community & Adoption
Does the project have users, downloads, attention, and a welcoming setup for contributors?
Popularity & adoption
How it's scored
| 55.1/60 | Stars — 2,480 stars |
| 21.1/25 | Forks — 341 forks |
| 9/15 | Watchers — 42 watchers |
Inputs used
| forks | 341 |
| stars | 2,480 |
| watchers | 42 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Community health
How it's scored
| 22.5/22.5 | README |
| 22.5/22.5 | License — recognized license (Apache-2.0) |
| 18/18 | CONTRIBUTING guide |
| 13.5/13.5 | Code of conduct |
| 0/7.2 | Issue template |
| 0/6.3 | PR template |
Inputs used
| has_readme | yes |
| has_license | yes |
| readme_badges | 5 |
| has_contributing | yes |
| has_issue_template | no |
| has_code_of_conduct | yes |
| readme_badge_services | github.com, shields.io |
| has_pull_request_template | no |
Ecosystem adoption (downloads)
How it's scored
| 80/80 | Monthly downloads — 3,670,360 downloads/month across pypi |
| 0/20 | Registry dependents — not reported by this ecosystem |
Inputs used
| packages | evaluate |
| dependents | — |
| ecosystems | pypi |
| total_downloads | — |
| monthly_downloads | 3,670,360 |
| unverified_packages_excluded | — |
Sustainability & Governance
Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?
How it's scored
| 36/54 | Bus factor — 3 contributor(s) cover half of all commits |
| 15.9/22.5 | Commit distribution — top contributor authored 29% of commits |
| 13.5/13.5 | Contributor breadth — 100 contributors |
| 0/10 | OpenSSF Scorecard: Contributors — no data |
Inputs used
| bus_factor | 3 |
| contributors_sampled | 100 |
| top_contributor_share | 0.293 |
How it's scored
| 18.2/42 | Issue resolution — 43% of issues closed |
| 23.6/30 | PR acceptance — 274/349 decided PRs merged |
| 0/13 | Newcomer PR acceptance — 0/11 first-time contributors' PRs merged in 30d |
| 0/15 | OpenSSF Scorecard: Code-Review — no data |
Inputs used
| merged_prs | 274 |
| open_issues | 194 |
| closed_issues | 149 |
| prs_merged_7d | 0 |
| prs_decided_7d | 0 |
| prs_merged_30d | 0 |
| prs_decided_30d | 11 |
| issue_closed_ratio | 0.434 |
| closed_unmerged_prs | 75 |
| first_time_authors_30d | 2 |
| first_time_prs_merged_30d | 0 |
| first_time_prs_decided_30d | 11 |
Ownership & stewardship
How it's scored
| 30/30 | Ownership backing — organization-owned |
| 20/20 | Verified domain |
| 25/25 | Owner reach — 68,212 followers of huggingface |
| 25/25 | Track record — 467 public repos, account ~9 yr old |
Inputs used
| followers | 68,212 |
| owner_type | Organization |
| is_verified | yes |
| owner_login | huggingface |
| public_repos | 467 |
| account_age_days | 3,497 |
Package maintenance
How it's scored
| 25/25 | Published & resolvable — 1 package(s) on pypi |
| 26/35 | Publish recency — latest publish 357 days ago |
| 20/20 | Version history — 14 published versions |
| 20/20 | Not deprecated — active, not deprecated or yanked |
Inputs used
| packages | evaluate |
| ecosystems | pypi |
| any_deprecated | no |
| min_days_since_publish | 357 |
Engineering Quality
Are baseline engineering and documentation practices in place?
Engineering practices
How it's scored
| 24/24 | CI workflows — 7 workflow(s) |
| 24/24 | Tests present |
| 16/16 | Linter config — setup.cfg ([flake8], [isort]) |
| 0/9.6 | Pre-commit hooks |
| 0/6.4 | .editorconfig |
| 0/20 | OpenSSF Scorecard: CI-Tests — no data |
Inputs used
| has_ci | yes |
| has_tests | yes |
| has_editorconfig | no |
| has_linter_config | yes |
| has_precommit_config | no |
Documentation
How it's scored
| 30/30 | README |
| 25/25 | Documentation directory |
| 15/15 | Documentation / homepage site — https://huggingface.co/docs/evaluate |
| 10/10 | Repository description |
| 10/10 | Topics — 2 topics |
| 10/10 | Wiki |
Inputs used
| topics | evaluation, machine-learning |
| has_wiki | yes |
| homepage | https://huggingface.co/docs/evaluate |
| docs_site | https://huggingface.co/docs/evaluate |
| has_readme | yes |
| has_docs_dir | yes |
| has_description | yes |
Security
Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?
Security posture
How it's scored
| 0/30 | Security policy (SECURITY.md) |
| 0/25 | Dependabot config |
| 0/25 | Dependency lockfiles |
| 0/20 | CodeQL workflow |
Inputs used
| source | file_signals |
| lockfiles | — |
| manifests | setup.cfg, setup.py |
| has_codeql_workflow | no |
| has_security_policy | no |
| has_dependabot_config | no |
Dependency advisories
How it's scored
| 35/35 | Direct dependencies free of known advisories — no direct dependency carries a known advisory |
| 25/25 | Indirect dependencies free of known advisories — no indirect dependency carries a known advisory |
| 0/40 | No advisories left outstanding — no advisory carries a publication date |
Inputs used
| source | osv |
| advisories | 0 |
| affected_packages | 0 |
| assessed_packages | 35 |
| unassessed_packages | 0 |
| affected_by_severity | none |
| direct_affected_packages | 0 |
AI Readiness
How well is the repo equipped to be developed and maintained with AI coding agents? Carries a deliberately small weight (4%): agent tooling is a real maintenance signal, but a repository with none can still reach 100/100.
Agent context & guidance
How it's scored
| 0/45 | Agent instructions — no CLAUDE.md / AGENTS.md / editor rules |
| 0/15 | Machine-readable docs (llms.txt) |
| 40/40 | Legible commit history — 89 of 100 human commits state their intent (structured subject or explanatory body) |
Inputs used
| has_llms_txt | no |
| llms_txt_url | — |
| legible_history_share | 0.89 |
| agent_instruction_files | — |
| agent_instruction_max_bytes | — |
Verify loop (build / test / typecheck)
How it's scored
| 18/18 | One-command bootstrap — Makefile |
| 22/22 | Automated tests |
| 11/11 | Lint / format config — setup.cfg ([flake8], [isort]) |
| 0/11 | Static type checking |
| 0/10 | Reproducible environment |
| 0/10 | Demonstrated agent practice — no agent-authored commits among the last 100 |
| 0/8 | Automated maintenance — no automated dependency updates observed |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — no data |
Inputs used
| has_nix | no |
| has_tests | yes |
| lockfiles | — |
| has_dockerfile | no |
| typed_language | no |
| bootstrap_files | Makefile |
| has_devcontainer | no |
| has_linter_config | yes |
| typecheck_configs | — |
| agent_commit_share | 0 |
| toolchain_manifests | — |
| dependency_bot_commit_share | 0 |
Code legibility for models
How it's scored
| 0/45 | Type-checkable code — Python without a type-check config |
| 55/55 | Manageable file sizes — 0/188 source files over 60KB |
Inputs used
| primary_language | Python |
| largest_source_bytes | 46,420 |
| source_files_sampled | 188 |
| oversized_source_files | 0 |
Key facts
Data collection warnings
- Star history unavailable: GitHub GraphQL error: Resource not accessible by personal access token
- OpenSSF Scorecard did not return a usable result (killed by SIGKILL — most likely the container's memory limit; 2026/09/10 21:42:12 Warning: PATs stored in env variables GITHUB_AUTH_TOKEN and GITHUB_TOKEN differ. Scorecard will use the former.); skipping Scorecard checks
More detail
Star and fork history 0 ★ / 341 ⇿
When each star and fork was added, collected from GitHub and bucketed by day. Cumulative growth sits directly above the daily additions it is made of, so the two read against each other: steady organic accretion looks nothing like an abrupt, short-lived burst. Where that difference is measurable, it is reported as growth authenticity.
Each point covers 4 days.
All dependencies 33
Full resolved dependency set from the GitHub dependency graph: 0 direct and 33 indirect (transitive) packages. The transitive closure is complete when the repository commits a lockfile.
| Registry | Package | Version | Relation |
|---|---|---|---|
| PyPI | absl-py | — | indirect |
| PyPI | bert-score | — | indirect |
| PyPI | cer | — | indirect |
| PyPI | charcut | — | indirect |
| PyPI | datasets | — | indirect |
| PyPI | dill | — | indirect |
| PyPI | faiss-cpu | — | indirect |
| PyPI | fsspec | — | indirect |
| PyPI | gin-config | — | indirect |
| PyPI | huggingface-hub | — | indirect |
| PyPI | importlib-metadata | — | indirect |
| PyPI | jiwer | — | indirect |
| PyPI | mauve-text | — | indirect |
| PyPI | multiprocess | — | indirect |
| PyPI | nltk | — | indirect |
| PyPI | numpy | — | indirect |
| PyPI | packaging | — | indirect |
| PyPI | pandas | — | indirect |
| PyPI | requests | — | indirect |
| PyPI | rouge-score | — | indirect |
| PyPI | sacrebleu | — | indirect |
| PyPI | sacremoses | — | indirect |
| PyPI | scikit-learn | — | indirect |
| PyPI | scipy | — | indirect |
| PyPI | seqeval | — | indirect |
| PyPI | tensorflow | — | indirect |
| PyPI | torch | — | indirect |
| PyPI | tqdm | — | indirect |
| PyPI | transformers | — | indirect |
| PyPI | trectools | — | indirect |
| PyPI | unbabel-comet | — | indirect |
| PyPI | unidecode | 1.3.4 | indirect |
| PyPI | xxhash | — | indirect |
Dependency advisories 0
Installing pypi:evaluate@0.4.6 pulls in 35 packages, direct and transitive: 0 carry known advisories, of which 0 are direct dependencies.
No known advisories affect the assessed dependencies.
An advisory means the version recorded in the dependency graph falls inside an advisory’s affected range. Reachability is not analysed, and the graph includes development and test pins — a finding may concern tooling rather than shipped software.
Raw JSON report machine-readable
Feedback
Spotted something off in this report, or have thoughts to share? Wrong measurements, missed tooling, ideas, questions — anything is welcome. Every message is read and gets a response.
Scores are signals, not warranties. They reflect publicly visible practices on GitHub — not a code audit, and not a security guarantee.
Missing data is excluded and weights renormalized, never scored as zero. Methodology is versioned and open: metrics v2.10.0, schema v0.34.0 — full methodology · metrics wiki.
How one result sits in the wider record: aggregate statistics — PyPI.