CLUEbenchmark
CLUE benchmark Joined Nov 2019 View on GitHub
- Stars
- 19,652
- across 50 public repos
- Rank
- #1,894
- of 94,827 organizations, top 2%
- New on the board this week
Repositories with 50+ stars
| Rank | Repository | Language | Stars |
|---|---|---|---|
| 14,710 | 搜索所有中文NLP数据集，附常用英文NLP数据集 | Python | 4,457 |
| 15,353 | 中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard | Python | 4,289 |
| 20,320 | SuperCLUE: 中文通用大模型综合性基准 | A Benchmark for Foundation Models in Chinese | 3,308 | |
| 44,875 | CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition | Python | 1,526 |
| 65,011 | Large-scale Pre-training Corpus for Chinese 100G 中文预训练语料 | 1,024 | |
| 80,651 | 高质量中文预训练模型集合：最先进大模型、最快小模型、相似度专门模型 | Python | 810 |
| 121,835 | FewCLUE 小样本学习测评基准，中文版 | Python | 517 |
| 123,686 | pCLUE: 1000000+多任务提示学习数据集 | Jupyter Notebook | 508 |
| 135,817 | KgCLUE: 大规模中文开源知识图谱问答 | Python | 457 |
| 188,926 | 3000000+语义理解与匹配数据集。可用于无监督对比学习、半监督学习等构建中文领域效果最好的预训练模型 | Python | 314 |
| 231,838 | Chinese Language Generation Evaluation 中文生成任务基准测评 | Python | 247 |
| 322,286 | OCNLI: 中文原版自然语言推理任务 | Python | 166 |
| 346,519 | SC-Safety: 中文大模型多轮对抗安全基准 | 152 | |
| 362,231 | DataCLUE: 数据为中心的NLP基准和工具包 | Python | 144 |
| 368,441 | 中文 预训练 ELECTRA 模型: 基于对抗学习 pretrain Chinese Model | 141 | |
| 368,441 | SuperCLUE琅琊榜：中文通用大模型匿名对战评价基准 | 141 | |
| 384,071 | Python toolkit for Chinese Language Understanding(CLUE) Evaluation benchmark | Python | 134 |
| 386,340 | 中文原生检索增强生成测评基准 | 133 | |
| 400,912 | Llama2开源模型中文版-全方位测评，基于SuperCLUE的OPEN基准 | Llama2 Chinese evaluation with SuperCLUE | 127 | |
| 499,806 | SuperCLUE-Agent: 基于中文原生任务的Agent智能体核心能力测评基准 | 96 | |
| 503,963 | DistilBERT for Chinese 海量中文预训练蒸馏bert模型 | 95 | |
| 535,290 | QBQTC: 大规模搜索匹配数据集 | Python | 88 |
| 566,050 | 一站式自动化开源标注平台 | Java | 82 |
| 566,050 | 中文通用大模型开放域多轮测评基准 | An Open Domain Benchmark for Foundation Models in Chinese | 82 | |
| 577,196 | CLUEWSC2020: WSC Winograd模式挑战中文版，中文指代消解任务 | 80 | |
| 713,786 | SuperCLUE-Math6：新一代中文原生多轮多步数学推理数据集的探索之旅 | Python | 61 |
| 723,122 | 离线端阅读理解应用 QA for mobile, Android & iPhone | Python | 60 |
| 723,122 | 高性能小模型测评 Shared Tasks in NLPCC 2020. Task 1 - Light Pre-Training Chinese Language Model for NLP Task | Python | 60 |
| 732,723 | 零样本学习测评基准，中文版 | Python | 59 |
Among 94,827 organizations
16k–25k stars: 924 organizations, including CLUEbenchmark
Stars along the bottom, and organizations in each band on a log scale
Where the stars are
Languages
- Python 13.4k stars, 68% · 16 repos
- Jupyter Notebook 508 stars, 3% · 1 repo
- Java 82 stars, <1% · 1 repo
When they were made
29 repos with 50+ stars, made between 2019 and 2024
Quick stats
- Next rank
- +27 stars to reach #1,893
- Next milestone
- +15,321 stars to reach the top 1%
- Public repos
- 50, 29 with 50+ stars
- Popular repos
- 19 over 100 stars, 5 over 1k stars
- Top repo
- CLUEDatasetSearch, #14,710 of all repos, 23% of stars
- Smaller repos
- 294 stars from repos under 50