EuroEval

license

MIT(OSI)

source

public(GitHub)

core features withheld

no

MIT and fully public: the LICENSE body is the stock MIT text (copyright Dan Saattrup Smart and Alexandra Instituttet A/S) with no appended terms. The package installs from PyPI, dataset-creation scripts ship in the repo, and no pricing, paid tier or license key appears in the README or on the docs site.

• https://api.github.com/repos/EuroEval/EuroEval/license recorded 2026-09-01

  GitHub's license endpoint reports spdx_id MIT and returns the stock MIT text (Copyright (c) 2021-2026 Dan Saattrup Smart; Copyright (c) 2022-2026 Alexandra Instituttet A/S) with no appended terms

• https://raw.githubusercontent.com/EuroEval/EuroEval/main/LICENSE recorded 2026-10-07

  LICENSE body, read in full: the stock MIT text under "Copyright (c) 2021-2026 Dan Saattrup Smart" and "Copyright (c) 2022-2026 Alexandra Instituttet A/S", with no appended terms.

• https://raw.githubusercontent.com/EuroEval/EuroEval/main/README.md recorded 2026-10-07

  README documents the open framework "(formerly known as ScandEval)", an "Installation and usage" section, and "Reproducing the evaluation datasets" from scripts in the "src/scripts/dataset_creation" folder; no pricing, paid tier or license key.

EuroEval's PyPI downloads are the adoption signal here, and the package is the project's documented install path. The legacy scandeval name, retained from before the rename, still draws its own downloads, but the two channels combined still add up to a small count.

• https://pypi.org/pypi/euroeval/json recorded 2026-09-01

  project_urls.Repository = github.com/EuroEval/EuroEval, author Dan Saattrup Smart <dan.smart@alexandra.dk>, version 18.0.0 uploaded 2026-08-14 — the package is the product

• https://pypistats.org/api/packages/euroeval/recent recorded 2026-09-01

  last_month = 750 downloads of the euroeval package

• https://pypistats.org/api/packages/scandeval/recent recorded 2026-09-01

  last_month = 2,207 downloads of the legacy scandeval package — recorded so the rename's second channel is visible; the sum stays under 10K

The deepest European-language coverage in the category — 30+ languages, all model classes, reproducible datasets and public leaderboards — but a single-domain harness with a narrow task surface and one primary maintainer, an order below lighteval's 1000+ tasks and backend spread, so one below lighteval beside bigcodebench and olmes.

• https://euroeval.com recorded 2026-10-07

  "the standard benchmark for evaluating language models across 30+ European languages"; supports encoders, decoders, encoder-decoders, base and instruction-tuned models; publisher Alexandra Institute; interactive leaderboards

• https://raw.githubusercontent.com/EuroEval/EuroEval/main/README.md recorded 2026-10-07

  README: "(formerly known as ScandEval)"; "All datasets used in this project are generated using the scripts located in the" src/scripts/dataset_creation folder, under a "Reproducing the evaluation datasets" section.