dustalov/evalica

Evalica, your favourite evaluation toolkit

55
/ 100
Established

Evalica is a toolkit for statisticians, researchers, and data analysts that helps quantify how well different items or ideas compare against each other, or how consistently multiple people rate things. You input structured data of comparisons (e.g., 'pizza' vs. 'burger' with a 'winner') or a matrix of ratings, and it outputs scores, ranks, or reliability metrics like Krippendorff's alpha. It's designed for anyone needing to objectively evaluate preferences or agreement from collected data.

Available on PyPI.

Use this if you need to rank items based on pairwise comparisons (like in competitive events or preference studies) or measure the agreement between multiple raters on a set of items.

Not ideal if your primary need is general-purpose statistical modeling beyond ranking, reliability, and uncertainty estimation.

statistical-analysis market-research survey-analysis quality-assurance evaluation-metrics
Maintenance 10 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 9 / 25

How are scores calculated?

Stars

62

Forks

5

Language

Python

License

Apache-2.0

Last pushed

Mar 10, 2026

Monthly downloads

19

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/dustalov/evalica"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.