LiveCodeBench

data

downloadable(HF parquet)

license

cc(the card YAML names the Creative Commons family and no variant

datasheet

present(README documents versions/sources/structure)

redistributable

yes

splits

public problems with hidden test cases bundled

Downloadable with a datasheet, but the only license statement the project makes about the corpus is a bare "cc" naming no variant, and CC-BY and CC-BY-NC sit two tiers apart. No variant is stated anywhere the project publishes: not in the card front matter, the Hub API, the sibling code_generation and test_generation corpora, the repository LICENSE (MIT, which covers the lcb_runner harness rather than the problems), the README, ERRATA.md, the project site, the leaderboard or the paper. Files that download freely without a grant to use them are not open, and not closed either, so this sits at gated - the barrier is the missing permission rather than a login. The problems are collected from LeetCode, AtCoder and Codeforces, which is a plausible reason no variant has been committed to.

• https://huggingface.co/datasets/livecodebench/code_generation_lite recorded 2026-08-13

  `license:cc` in the repo tags with no variant; the embedded repo state reads `"gated":false`, so the parquet downloads freely; the README/datasheet still renders the release_v1..v5 change log; 93,572 downloads in the trailing 30 days

• https://huggingface.co/datasets/livecodebench/code_generation_lite/blob/main/README.md recorded 2026-06-04

  YAML metadata license: cc

• https://huggingface.co/datasets/livecodebench/code_generation_lite/raw/main/README.md recorded 2026-08-13

  card front matter is `license: cc` with tags, pretty_name and size_categories, and nothing naming a Creative Commons variant; the body is a change log of release_v1..v5, a dataset description and usage instructions

• https://huggingface.co/api/datasets/livecodebench/code_generation_lite recorded 2026-08-13

  cardData.license is the string "cc" and the repository tags carry `license:cc`; the sibling corpora code_generation and test_generation carry the same bare `cc`, and execution carries no license at all. The open discussions on the repo are about loading, parquet conversion and version sizes - none asks or answers what the CC variant is

• https://raw.githubusercontent.com/LiveCodeBench/LiveCodeBench/main/LICENSE recorded 2026-08-13

  MIT License, copyright 2024 LiveCodeBench. This is the repository holding lcb_runner, the evaluation harness; the problems are distributed from the Hugging Face repos and this file makes no statement about them

• https://raw.githubusercontent.com/LiveCodeBench/LiveCodeBench/main/README.md recorded 2026-08-13

  217 lines covering install, running the harness, scenarios and submissions, with no licensing or terms section at all

91,719 Hugging Face downloads in the trailing 30 days for livecodebench/code_generation_lite, the single declared artifact, which puts it in the 10K-100K band, level 3 on the dataset adoption scale. That scale tops out at >1M.

• https://huggingface.co/api/datasets/livecodebench/code_generation_lite recorded 2026-08-13

  91,719 downloads in the trailing 30 days for livecodebench/code_generation_lite

A dataset is not 'capable', so this axis is left unscored. Its contamination resistance - the "live", continuously updated design - is a real quality strength, but openness and adoption are what carry this category.

• https://huggingface.co/datasets/livecodebench/code_generation_lite recorded 2026-08-13

  a static release-versioned problem corpus with hidden test cases bundled; no performance, throughput or feature claim on the page for the capability axis to read