PyRank
UKGovernmentBEIS

inspect-evals

Collection of evals for Inspect AI
PyPI GitHub
More links
Download Stats Changelog Documentation Issue Tracker Release Notes
Verified repo
Monthly downloads
916.6K
Weekly downloads
223.1K
GitHub stars
698

Downloads in the 30 and 7 days to October 10, 2026. Refreshed weekly.

Package Information

Latest Version
0.24.0
Requires Python
>=3.11
Licence
MIT
Last Release
1 week ago
Author
UK AI Security Institute
First Release
October 22, 2025
Total Releases
35
Python Versions
3
No reported malware or high/critical advisories · Details

The current version has no OSV.dev malware reports and no critical or high-severity vulnerabilities.

Package Insights

What's this?
Score breakdown - each component scores 0-100, weighted by percentage
Maintenance
100
Popularity
66
Adoption
79
Community
100
Provenance
100
How the maintenance status was determined
Last commit
7 days ago
Monthly downloads
916,637
• Active
Activity within 30 days
Stable
Activity within 31-180 days
Minimal
Activity within 181-365 days, or no activity data
At Risk
No activity for > 365 days, but > 10,000 monthly downloads
Archived
Repository flagged as archived on GitHub
How the popularity category was determined
Monthly downloads
916,637
Stars
698
Stars per 1k downloads
0.76
Industry Standard
> 10,000,000 monthly downloads
Hidden Gem
< 0.5 stars per 1k downloads and > 100,000 monthly downloads
Community Favorite
> 5 stars per 1k downloads
• Rising Star
Balanced ratio of stars to downloads
Unknown
Fewer than 1,000 monthly downloads, or no star data
How download momentum is calculated
Week daily avg
31,865
Month daily avg
30,555
Momentum
+4.3%
((week_daily_avg - month_daily_avg) / month_daily_avg) * 100
More insights and metrics
Python version support tiers
requires_python
>=3.11
Cutting Edge
Minimum supported version is 3.14 or newer
• Modern
Minimum supported version is 3.11 to 3.13
Legacy
Supports 3.10 or older (or Python 2)
Unknown
No requires_python specified or unparseable
License categories
License
MIT
• Permissive
MIT, Apache, BSD, ISC, Unlicense, CC0, etc.
Copyleft
GPL, LGPL, AGPL, MPL, EPL, etc.
Proprietary
Commercial, all rights reserved, custom EULAs
Unknown
No license specified, or none of the above match
How the release cadence was determined
Last release
7 days ago
Total releases
35
Releases/year
35.6
• Rapid
Last release within 365 days and > 12 releases/year
Regular
Last release within 365 days
Slow
Last release 366-730 days ago
Stalled
Last release > 730 days ago, or no releases
Unknown
No usable release date available
How contributor risk was determined
Contributors
236
Monthly downloads
916,637
High Load
≤ 2 contributors and ≥ 50,000 monthly downloads
Moderate Load
< 10 contributors and ≥ 500,000 monthly downloads
Low Load
< 25 contributors and ≥ 5,000,000 monthly downloads, or sole maintainer with ≥ 10,000 monthly downloads
• Balanced
Enough contributors for the package's popularity
Unknown
No contributor data available
Engagement
80
 
Issue Burden
210.6
per 1k stars
Discussions
0.0
per 1k stars
Fork Ratio
51.5%
contrib / forks
Stale Release
No
 
PR Velocity
Quiet
 
Not all downloads include detailed metadata. Breakdowns reflect the subset that does.

Downloads by OS

Linux 16.4K
macOS 386
Windows 22

Python Versions

3.13
87.7% 14.7K
3.12
10.9% 1.8K
3.14
0.9% 147
3.11
0.4% 68
3.10
0.1% 14

Top Countries

1. US US
16.7K
2. HK HK
54
3. BE BE
36
4. GB GB
33
5. JP JP
15
6. CA CA
11
7. CN CN
11
8. IN IN
10
9. MX MX
9
10. DE DE
7

Weekly Downloads

GitHub Stars

Dependencies

14
95 optional dependencies
  • antlr4-python3-runtime~=4.11.0[math]
    extra == "math"
  • beautifulsoup4>=4.12.0[bfcl-v4]
    extra == "bfcl-v4"
  • beautifulsoup4[mind2web]
    extra == "mind2web"
  • bioc[medqa]
    extra == "medqa"
  • bs4[agentic-misalignment]
    extra == "agentic-misalignment"
  • cje-eval>=0.6.0[cje]
    extra == "cje"
  • click[b3]
    extra == "b3"
  • deepdiff[agentdojo]
    extra == "agentdojo"
  • docker[swe-bench]
    extra == "swe-bench"
  • docker[swe-lancer]
    extra == "swe-lancer"
  • drain3[paperbench]
    extra == "paperbench"
  • faiss-cpu>=1.8.0[bfcl-v4]
    extra == "bfcl-v4"
  • filelock[gaia]
    extra == "gaia"
  • filelock[osworld]
    extra == "osworld"
  • filelock[cti-realm]
    extra == "cti-realm"
  • gdown>=6[gdown]
    extra == "gdown"
  • gensim[sciknoweval]
    python_version < "3.13" and extra == "sciknoweval"
  • google-genai>=1.56.0[gdm-capabilities]
    extra == "gdm-capabilities"
  • google-search-results>=2.4.2[bfcl-v4]
    extra == "bfcl-v4"
  • h5py[scicode]
    extra == "scicode"
  • html2text>=2024.2.26[bfcl-v4]
    extra == "bfcl-v4"
  • httpx[cti-realm]
    extra == "cti-realm"
  • huggingface-hub[gdpval]
    extra == "gdpval"
  • huggingface-hub[personality]
    extra == "personality"
  • immutabledict[gdm-stealth]
    extra == "gdm-stealth"
  • inspect-cyber==0.1.0[cybench]
    extra == "cybench"
  • inspect-cyber>=0.1.0[cybergym]
    extra == "cybergym"
  • inspect-cyber[theagentcompany]
    extra == "theagentcompany"
  • inspect-evals[sciknoweval]
    extra == "sciknoweval"
  • inspect-evals[usaco]
    extra == "usaco"
  • inspect-evals[scicode]
    extra == "scicode"
  • inspect-swe[scbench]
    extra == "scbench"
  • instruction-following-eval[ifeval]
    extra == "ifeval"
  • jieba==0.42.1[sevenllm]
    extra == "sevenllm"
  • jsonlines[swe-bench]
    extra == "swe-bench"
  • langdetect[ifeval]
    extra == "ifeval"
  • lxml[mind2web]
    extra == "mind2web"
  • lxml-stubs[mind2web]
    extra == "mind2web"
  • matplotlib[anima]
    extra == "anima"
  • mpmath[bfcl]
    extra == "bfcl"
  • nltk[sciknoweval]
    extra == "sciknoweval"
  • nltk[makemesay]
    extra == "makemesay"
  • odfpy>=1.4.1[theagentcompany]
    extra == "theagentcompany"
  • openai[b3]
    extra == "b3"
  • openpyxl[theagentcompany]
    extra == "theagentcompany"
  • overrides>=7.7.0[bfcl-v4]
    extra == "bfcl-v4"
  • pandas[gdm-stealth]
    extra == "gdm-stealth"
  • pandas[niah]
    extra == "niah"
  • pandas[theagentcompany]
    extra == "theagentcompany"
  • pandas[worldsense]
    extra == "worldsense"
  • pdf2image[cyberseceval-4]
    extra == "cyberseceval-4"
  • pip[scbench]
    extra == "scbench"
  • platformdirs[cyberseceval-4]
    extra == "cyberseceval-4"
  • psutil[cti-realm]
    extra == "cti-realm"
  • pydantic[agentdojo]
    extra == "agentdojo"
  • pygithub>=2.0[register-tooling]
    extra == "register-tooling"
  • pypdf[cyberseceval-4]
    extra == "cyberseceval-4"
  • pypdf[theagentcompany]
    extra == "theagentcompany"
  • pypdf>=5.1.0[register-tooling]
    extra == "register-tooling"
  • python-dateutil[gdm-stealth]
    extra == "gdm-stealth"
  • python-dateutil[gdm-capabilities]
    extra == "gdm-capabilities"
  • python-dotenv[b3]
    extra == "b3"
  • python-pptx[theagentcompany]
    extra == "theagentcompany"
  • pyyaml[cyberseceval-4]
    extra == "cyberseceval-4"
  • rank-bm25>=0.2.2[bfcl-v4]
    extra == "bfcl-v4"
  • rdchiral[sciknoweval]
    extra == "sciknoweval"
  • rdkit[sciknoweval]
    extra == "sciknoweval"
  • requests[cti-realm]
    extra == "cti-realm"
  • rich[gdm-self-proliferation]
    extra == "gdm-self-proliferation"
  • rich[gdm-capabilities]
    extra == "gdm-capabilities"
  • rouge==1.0.1[sevenllm]
    extra == "sevenllm"
  • rouge-score[b3]
    extra == "b3"
  • rouge-score[sciknoweval]
    extra == "sciknoweval"
  • sacrebleu[cyberseceval-4]
    extra == "cyberseceval-4"
  • scikit-learn[healthbench]
    extra == "healthbench"
  • scikit-learn[theagentcompany]
    extra == "theagentcompany"
  • scipy[gdm-stealth]
    extra == "gdm-stealth"
  • scipy[sciknoweval]
    extra == "sciknoweval"
  • scipy[scicode]
    extra == "scicode"
  • scipy[core-bench]
    extra == "core-bench"
  • semgrep>1.68[cyberseceval-4]
    extra == "cyberseceval-4"
  • sentence-transformers>=3.0.0[bfcl-v4]
    extra == "bfcl-v4"
  • sentence-transformers>=5.1.1[sevenllm]
    extra == "sevenllm"
  • swebench>=3.0.15[swe-bench]
    extra == "swe-bench"
  • sympy[scicode]
    extra == "scicode"
  • sympy[math]
    extra == "math"
  • tabulate[gdm-stealth]
    extra == "gdm-stealth"
  • tenacity[b3]
    extra == "b3"
  • tf-keras[sevenllm]
    python_version < "3.13" and extra == "sevenllm"
  • tree-sitter[ifevalcode]
    extra == "ifevalcode"
  • tree-sitter-cpp[ifevalcode]
    extra == "ifevalcode"
  • types-beautifulsoup4[mind2web]
    extra == "mind2web"
  • types-docker[swe-lancer]
    extra == "swe-lancer"
  • vimgolf==0.5.1[vimgolf]
    extra == "vimgolf"
  • vimgolf==0.5.1[vimgolf-challenges]
    extra == "vimgolf-challenges"

Used By

7

Repository details

Forks
458
Issues
147
Last Commit
1 week ago
Contributors
236
Open PRs
104
Archived
No

Data and sources

Tracking Since
September 26, 2026
Data Updated
October 11, 2026
Data Freshness
Fresh
Sources and methodology