# ChineseGLUE/ChineseGLUE

Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard

Repository: https://github.com/ChineseGLUE/ChineseGLUE
Canonical: https://ross.abutalabs.com/products/chineseglue
Homepage: https://www.CLUEbenchmarks.com
Language: Python
License Family: other
Topics: glue, language-understanding, bert, pre-trained-model, chinese-corpus, nlp, albert, datasets
Last push: 2023-02-18T17:35:23+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2524, "days_push": 1292, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1782, forks 244 (observed 2026-08-28T04:05:35.670224+00:00)

## What it is
ChineseGLUE is a language understanding evaluation benchmark for Chinese, providing datasets, baseline pre-trained models, corpora, and a public leaderboard. It covers tasks like text classification, sentence-pair matching, NER, and reading comprehension, and has largely been superseded by the CLUE benchmark project.

## Use cases
- evaluate Chinese language understanding models
- benchmark pretrained models like BERT on Chinese NLP tasks
- find Chinese NLP datasets for classification and reading comprehension
- compare Chinese pretrained model performance on a leaderboard
- get Chinese corpora for language model pretraining
- test Chinese NER and sentence matching models

## When to choose
- you need standardized Chinese NLP benchmark datasets and baselines
- you want to compare Chinese pretrained models like BERT, ERNIE, RoBERTa, ALBERT
- you need Chinese corpora for pretraining or language modeling

## When to avoid
- you need actively maintained benchmarks - the successor CLUE project is recommended
- you work with languages other than Chinese
- you need large language model evaluation rather than classic NLU tasks

## Facets
- artifact type: dataset
- maturity: maintenance
- function: machine-learning, nlp, benchmarking, data-science
- domain: machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: chinese-nlp, benchmark, glue, pretrained-models, leaderboard, text-classification, reading-comprehension, named-entity-recognition, natural-language-processing, datasets

## Member repositories
- ChineseGLUE/ChineseGLUE (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:35.670224+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:24:20.060307+00:00, confidence not recorded.
  - readme: https://github.com/ChineseGLUE/ChineseGLUE (fetched 2026-08-28T04:05:35.670224+00:00, sha 3a6e0af40b97)
  - homepage: https://www.CLUEbenchmarks.com (fetched 2026-08-29T11:02:57.353458+00:00, sha c50fdfe38b8c)
  - site_page: https://www.cluebenchmarks.com/aboutClue.html (fetched 2026-08-29T11:02:57.362826+00:00, sha b318c2db06a4)
- Data as of 2026-08-30T08:39:29.467469+00:00.