CircleCI-Research / evalbench
Evaluate LLMs side-by-side. Benchmark AI models and coding agents across providers like OpenAI, Google, Anthropic, DeepSeek, and more. Supports custom tasks, structured JSON responses, tool use, and LLM-as-judge validation. Originally created by Petr Malik as MindTrial.
CircleCI-Research/evalbench holds a health index of 42 out of 100, placing it in the Weak band. It scores highest on AI Readiness (71/100) and lowest on Community & Adoption (12/100). It was last updated 177 days ago. A single contributor accounts 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 45 is calibrated to 42 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 |
|---|---|---|---|---|---|
| Go | github.com/CircleCI-Research/evalbench | v0.17.0 | - | 33 | 178 days ago |
Metrics by category
Vitality
Is the project alive — is code being written and are releases shipping?
Development activity
How it's scored
| 9.9/36 | Push recency — last push 177 days ago |
| 10.4/36 | Commit cadence — 15/52 weeks with commits |
| 16.5/18 | Commit volume — 67 commits in the last year |
| 0/10 | OpenSSF Scorecard: Maintained — 0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0 |
Inputs used
| commits_last_year | 67 |
| human_commit_share | 1 |
| days_since_last_push | 177 |
| active_weeks_last_year | 15 |
Release discipline
How it's scored
| 16.2/27 | Ships releases — 33 version tags (no GitHub releases) |
| 27/36 | Release recency — latest release 178 days ago |
| 27/27 | Release cadence — a release every ~13.2 days |
| 0/10 | OpenSSF Scorecard: Signed-Releases — no data |
Inputs used
| releases_count | 33 |
| latest_release_tag | v0.17.0 |
| releases_from_tags | yes |
| days_since_latest_release | 178 |
| mean_days_between_releases | 13.2 |
Community & Adoption
Does the project have users, downloads, attention, and a welcoming setup for contributors?
Popularity & adoption
How it's scored
| 0/60 | Stars — 0 stars |
| 0/25 | Forks — 0 forks |
| 0/15 | Watchers — 0 watchers |
Inputs used
| forks | 0 |
| stars | 0 |
| watchers | 0 |
| growth_state | unverified |
| growth_factor_pct | 100 |
| growth_unverified_reason | no_history |
Community health
How it's scored
| 0/22.5 | README |
| 22.5/22.5 | License — recognized license (MPL-2.0) |
| 0/18 | CONTRIBUTING guide |
| 0/13.5 | Code of conduct |
| 0/7.2 | Issue template |
| 0/6.3 | PR template |
Inputs used
| has_readme | no |
| has_license | no |
| readme_badges | 5 |
| has_contributing | no |
| has_issue_template | no |
| has_code_of_conduct | no |
| readme_badge_services | github.com, goreportcard.com, pkg.go.dev, shields.io |
| has_pull_request_template | no |
Sustainability & Governance
Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?
Maintainer resilience (bus factor)
How it's scored
| 9/54 | Bus factor — 1 contributor(s) cover half of all commits |
| 7.2/22.5 | Commit distribution — top contributor authored 68% of commits |
| 2.7/13.5 | Contributor breadth — 2 contributors |
| 6/10 | OpenSSF Scorecard: Contributors — project has 2 contributing companies or organizations -- score normalized to 6 |
Inputs used
| bus_factor | 1 |
| contributors_sampled | 2 |
| top_contributor_share | 0.681 |
How it's scored
| 0/42 | Issue resolution — no issues or no data |
| 30/30 | PR acceptance — 1/1 decided PRs merged |
| 0/13 | Newcomer PR acceptance — no first-time contributor's PR decided in 30d |
| 0/15 | OpenSSF Scorecard: Code-Review — Found 0/26 approved changesets -- score normalized to 0 |
Inputs used
| merged_prs | 1 |
| open_issues | 0 |
| closed_issues | 0 |
| prs_merged_7d | 0 |
| prs_decided_7d | 0 |
| prs_merged_30d | 0 |
| prs_decided_30d | 0 |
| issue_closed_ratio | — |
| closed_unmerged_prs | 0 |
| first_time_authors_30d | 0 |
| first_time_prs_merged_30d | 0 |
| first_time_prs_decided_30d | 0 |
Ownership & stewardship
How it's scored
| 30/30 | Ownership backing — organization-owned |
| 20/20 | Verified domain |
| 5/25 | Owner reach — 4 followers of CircleCI-Research |
| 15.2/25 | Track record — 9 public repos, account ~3 yr old |
Inputs used
| followers | 4 |
| owner_type | Organization |
| is_verified | yes |
| owner_login | CircleCI-Research |
| public_repos | 9 |
| account_age_days | 1,438 |
Package maintenance
How it's scored
| 25/25 | Published & resolvable — 1 package(s) on go |
| 35/35 | Publish recency — latest publish 178 days ago |
| 20/20 | Version history — 33 published versions |
| 20/20 | Not deprecated — active, not deprecated or yanked |
Inputs used
| packages | github.com/CircleCI-Research/evalbench |
| ecosystems | go |
| any_deprecated | no |
| min_days_since_publish | 178 |
Engineering Quality
Are baseline engineering and documentation practices in place?
Engineering practices
How it's scored
| 24/24 | CI workflows — 1 workflow(s) |
| 24/24 | Tests present |
| 0/16 | Linter config |
| 0/9.6 | Pre-commit hooks |
| 0/6.4 | .editorconfig |
| 20/20 | OpenSSF Scorecard: CI-Tests — 1 out of 1 merged PRs checked by a CI test -- score normalized to 10 |
Inputs used
| has_ci | yes |
| has_tests | yes |
| has_editorconfig | no |
| has_linter_config | no |
| has_precommit_config | no |
Documentation
How it's scored
| 0/30 | README |
| 0/25 | Documentation directory |
| 15/15 | Documentation / homepage site — https://loop.circleci.com |
| 0/10 | Repository description |
| 10/10 | Topics — 10 topics |
| 0/10 | Wiki |
Inputs used
| topics | ai, ai-agents, benchmark-framework, ci-cd, circleci, devops, evaluation-framework, evaluation-metrics, llm, model-comparison |
| has_wiki | no |
| homepage | https://loop.circleci.com |
| docs_site | https://loop.circleci.com |
| has_readme | no |
| has_docs_dir | no |
| has_description | no |
Security
Are visible security and supply-chain practices strong, without unresolved high-risk jurisdiction exposure?
Security posture
How it's scored
| 7.5/7.5 | Binary-Artifacts — no binaries found in the repo |
| 3.8/7.5 | Branch-Protection — branch protection is not maximal on development and all release branches |
| 2.5/2.5 | CI-Tests — 1 out of 1 merged PRs checked by a CI test -- score normalized to 10 |
| 0/2.5 | CII-Best-Practices — no effort to earn an OpenSSF best practices badge detected |
| 0/7.5 | Code-Review — Found 0/26 approved changesets -- score normalized to 0 |
| 1.5/2.5 | Contributors — project has 2 contributing companies or organizations -- score normalized to 6 |
| 10/10 | Dangerous-Workflow — no dangerous workflow patterns detected |
| 0/7.5 | Dependency-Update-Tool — no update tool detected |
| 0/5 | Fuzzing — project is not fuzzed |
| 2.5/2.5 | License — license file detected |
| 0/7.5 | Maintained — 0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0 |
| 0/5 | Packaging — no data |
| 0/5 | Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
| 0/5 | SAST — SAST tool is not run on all commits -- score normalized to 0 |
| 0/5 | Security-Policy — security policy file not detected |
| 0/7.5 | Signed-Releases — no data |
| 0/7.5 | Token-Permissions — detected GitHub workflow tokens with excessive permissions |
| 0/7.5 | Vulnerabilities — 50 existing vulnerabilities detected |
Inputs used
| source | openssf_scorecard |
| checks_evaluated | 16 |
| scorecard_version | v5.5.0 |
| checks_inconclusive | 2 |
| scorecard_aggregate | 3 |
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
| 45/45 | Agent instructions — AGENTS.md |
| 15/15 | Machine-readable docs (llms.txt) — llms.txt served by the project website (https://docs.anthropic.com/llms.txt) |
| 40/40 | Legible commit history — 96 of 100 human commits state their intent (structured subject or explanatory body) |
Inputs used
| has_llms_txt | yes |
| llms_txt_url | https://docs.anthropic.com/llms.txt |
| legible_history_share | 0.96 |
| agent_instruction_files | AGENTS.md |
| agent_instruction_max_bytes | 3,085 |
Verify loop (build / test / typecheck)
How it's scored
| 12.6/18 | One-command bootstrap — go.mod (toolchain convention, no task runner) |
| 22/22 | Automated tests |
| 0/11 | Lint / format config |
| 0/11 | Static type checking |
| 10/10 | Reproducible environment — lockfile |
| 10/10 | Demonstrated agent practice — 11 of the last 100 commits agent-authored or agent-credited |
| 0/8 | Automated maintenance — no automated dependency updates observed |
| 0/10 | OpenSSF Scorecard: Pinned-Dependencies — dependency not pinned by hash detected -- score normalized to 0 |
Inputs used
| has_nix | no |
| has_tests | yes |
| lockfiles | go.sum |
| has_dockerfile | no |
| typed_language | no |
| bootstrap_files | — |
| has_devcontainer | no |
| has_linter_config | no |
| typecheck_configs | — |
| agent_commit_share | 0.11 |
| toolchain_manifests | go.mod |
| dependency_bot_commit_share | 0 |
Code legibility for models
How it's scored
| 0/45 | Type-checkable code — HTML without a type-check config |
| 54.4/55 | Manageable file sizes — 5/442 source files over 60KB |
Inputs used
| primary_language | HTML |
| largest_source_bytes | 73,199 |
| source_files_sampled | 442 |
| oversized_source_files | 5 |
Key facts
Data collection warnings
- Community profile unavailable
- GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
More detail
OpenSSF Scorecard 3.0 / 10
Independent, tool-agnostic security assessment from the open-source OpenSSF Scorecard. Each check rewards a security practice, not a specific vendor's tool. Checks Scorecard could not determine are marked n/a and excluded from the security score (never counted as zero).
| 10 | Binary-Artifacts | no binaries found in the repo |
| 5 | Branch-Protection | branch protection is not maximal on development and all release branches |
| 10 | CI-Tests | 1 out of 1 merged PRs checked by a CI test -- score normalized to 10 |
| 0 | CII-Best-Practices | no effort to earn an OpenSSF best practices badge detected |
| 0 | Code-Review | Found 0/26 approved changesets -- score normalized to 0 |
| 6 | Contributors | project has 2 contributing companies or organizations -- score normalized to 6 |
| 10 | Dangerous-Workflow | no dangerous workflow patterns detected |
| 0 | Dependency-Update-Tool | no update tool detected |
| 0 | Fuzzing | project is not fuzzed |
| 10 | License | license file detected |
| 0 | Maintained | 0 commit(s) and 0 issue activity found in the last 90 days -- score normalized to 0 |
| n/a | Packaging | packaging workflow not detected |
| 0 | Pinned-Dependencies | dependency not pinned by hash detected -- score normalized to 0 |
| 0 | SAST | SAST tool is not run on all commits -- score normalized to 0 |
| 0 | Security-Policy | security policy file not detected |
| n/a | Signed-Releases | no releases found |
| 0 | Token-Permissions | detected GitHub workflow tokens with excessive permissions |
| 0 | Vulnerabilities | 50 existing vulnerabilities detected |
Direct dependencies 24
| Registry | Package | Version constraint | Manifest |
|---|---|---|---|
| Go | github.com/charmbracelet/x/term | v0.2.1 | go.mod |
| Go | github.com/containerd/errdefs | v1.0.0 | go.mod |
| Go | github.com/docker/docker | v28.5.2+incompatible | go.mod |
| Go | github.com/google/uuid | v1.6.0 | go.mod |
| Go | github.com/invopop/jsonschema | v0.13.0 | go.mod |
| Go | github.com/kaptinlin/jsonrepair | v0.2.8 | go.mod |
| Go | github.com/oklog/ulid/v2 | v2.1.1 | go.mod |
| Go | github.com/openai/openai-go/v3 | v3.26.0 | go.mod |
| Go | github.com/santhosh-tekuri/jsonschema/v6 | v6.0.2 | go.mod |
| Go | github.com/sethvargo/go-retry | v0.3.0 | go.mod |
| Go | github.com/stretchr/testify | v1.11.1 | go.mod |
| Go | golang.org/x/time | v0.14.0 | go.mod |
| Go | google.golang.org/genai | v1.48.0 | go.mod |
| Go | gopkg.in/validator.v2 | v2.0.1 | go.mod |
| Go | gopkg.in/yaml.v3 | v3.0.1 | go.mod |
| Go | github.com/anthropics/anthropic-sdk-go | v1.26.0 | go.mod |
| Go | github.com/charmbracelet/bubbles/v2 | v2.0.0-beta.1 | go.mod |
| Go | github.com/charmbracelet/bubbletea/v2 | v2.0.0-beta.1 | go.mod |
| Go | github.com/charmbracelet/lipgloss/v2 | v2.0.0-beta.1 | go.mod |
| Go | github.com/cohesion-org/deepseek-go | v1.3.3 | go.mod |
| Go | github.com/go-playground/validator/v10 | v10.30.1 | go.mod |
| Go | github.com/rs/zerolog | v1.34.0 | go.mod |
| Go | github.com/sergi/go-diff | v1.4.0 | go.mod |
| Go | golang.org/x/exp | v0.0.0-20260218203240-3dfff04db8fa | go.mod |
All dependencies not collected
The resolved dependency set could not be collected for this report: GitHub dependency-graph SBOM unavailable (404); the dependency graph may be disabled for this repository
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 — Go.