{"url":"/dataset/clue","name":"CLUE","full_name":"Chinese Language Understanding Evaluation Benchmark","description_markdown":"CLUE is a Chinese Language Understanding Evaluation benchmark. It consists of different NLU datasets. It is a community-driven project that brings together 9 tasks spanning several well-established single-sentence/sentence-pair classification tasks, as well as machine reading comprehension, all on original Chinese text.","description_withheld":null,"homepage":"https://www.cluebenchmarks.com/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/clue-a-chinese-language-understanding","title":"CLUE: A Chinese Language Understanding Evaluation Benchmark","first_author":"Liang Xu","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"},{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"},{"name":"Document Ranking","url":"/task/document-ranking","datasets_with_task":"/datasets/task/document-ranking"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CLUE (CMRC2018)","CLUE (AFQMC)","CLUE (OCNLI_50K)","CLUE (DRCD)","CLUE (CMNLI)","CLUE (WSC1.1)","CLUE (C3)","ClueWeb09-B","CLUE"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/clue/clue","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/clue","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":99,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-modelling-on-clue-afqmc","task":"Language Modelling","dataset_variant":"CLUE (AFQMC)","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLM-130B","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","metrics":{"Accuracy":"71.2"},"code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"thudm/glm-130b","url":"https://github.com/thudm/glm-130b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-modelling-on-clue-c3","task":"Language Modelling","dataset_variant":"CLUE (C3)","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLM-130B","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","metrics":{"Accuracy":"77.5"},"code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"thudm/glm-130b","url":"https://github.com/thudm/glm-130b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-modelling-on-clue-cmnli","task":"Language Modelling","dataset_variant":"CLUE (CMNLI)","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLM-130B","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","metrics":{"Accuracy":"77.0"},"code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"thudm/glm-130b","url":"https://github.com/thudm/glm-130b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-modelling-on-clue-cmrc2018","task":"Language Modelling","dataset_variant":"CLUE (CMRC2018)","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLM-130B","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","metrics":{"Accuracy":"55.7"},"code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"thudm/glm-130b","url":"https://github.com/thudm/glm-130b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-modelling-on-clue-drcd","task":"Language Modelling","dataset_variant":"CLUE (DRCD)","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLM-130B","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","metrics":{"Accuracy":"77.1"},"code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"thudm/glm-130b","url":"https://github.com/thudm/glm-130b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-modelling-on-clue-ocnli-50k","task":"Language Modelling","dataset_variant":"CLUE (OCNLI_50K)","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLM-130B","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","metrics":{"Accuracy":"74.7"},"code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"thudm/glm-130b","url":"https://github.com/thudm/glm-130b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/language-modelling-on-clue-wsc1-1","task":"Language Modelling","dataset_variant":"CLUE (WSC1.1)","rows":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"GLM-130B","paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","metrics":{"Accuracy":"83.9"},"code_links":[{"title":"thudm/chatglm2-6b","url":"https://github.com/thudm/chatglm2-6b"},{"title":"thudm/chatglm3","url":"https://github.com/thudm/chatglm3"},{"title":"thudm/chatglm","url":"https://github.com/thudm/chatglm"},{"title":"modelscope/modelscope","url":"https://github.com/modelscope/modelscope"},{"title":"thudm/glm-130b","url":"https://github.com/thudm/glm-130b"},{"title":"THUDM/GLM","url":"https://github.com/THUDM/GLM"},{"title":"jackaduma/ChatGLM-LoRA-RLHF-PyTorch","url":"https://github.com/jackaduma/ChatGLM-LoRA-RLHF-PyTorch"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/glm3"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-ranking-on-clueweb09-b","task":"Document Ranking","dataset_variant":"ClueWeb09-B","rows":1,"metrics":["ERR@20","nDCG@20"],"first_row_in_archive_order":{"model":"XLNet","paper":"/paper/xlnet-generalized-autoregressive-pretraining","metrics":{"ERR@20":"20.28","nDCG@20":"31.10"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"PaddlePaddle/PaddleNLP","url":"https://github.com/PaddlePaddle/PaddleNLP/tree/develop/examples/language_model/xlnet"},{"title":"zihangdai/xlnet","url":"https://github.com/zihangdai/xlnet"},{"title":"kaushaltrivedi/fast-bert","url":"https://github.com/kaushaltrivedi/fast-bert"},{"title":"utterworks/fast-bert","url":"https://github.com/utterworks/fast-bert"},{"title":"graykode/xlnet-Pytorch","url":"https://github.com/graykode/xlnet-Pytorch"},{"title":"facebookresearch/anli","url":"https://github.com/facebookresearch/anli"},{"title":"lvyufeng/bert4ms","url":"https://github.com/lvyufeng/bert4ms/blob/master/bert4ms/models/xlnet.py"},{"title":"huggingface/xlnet","url":"https://github.com/huggingface/xlnet"},{"title":"cuhksz-nlp/SAPar","url":"https://github.com/cuhksz-nlp/SAPar"},{"title":"joshuaWang-bit/Textclassification-pytorch","url":"https://github.com/joshuaWang-bit/Textclassification-pytorch"},{"title":"fanchenyou/transformer-study","url":"https://github.com/fanchenyou/transformer-study"},{"title":"https-seyhan/BugAI","url":"https://github.com/https-seyhan/BugAI"},{"title":"NathanDuran/Sentence-Encoding-for-DA-Classification","url":"https://github.com/NathanDuran/Sentence-Encoding-for-DA-Classification"},{"title":"2miatran/Natural-Language-Processing","url":"https://github.com/2miatran/Natural-Language-Processing"},{"title":"chesterdu/contrastive_summary","url":"https://github.com/chesterdu/contrastive_summary"},{"title":"pauldevos/python-notes","url":"https://github.com/pauldevos/python-notes"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/5/xlnet"},{"title":"MindCode-4/code-5","url":"https://github.com/MindCode-4/code-5/tree/main/xlnet"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/1/xlnet"},{"title":"samwisegamjeee/pytorch-transformers","url":"https://github.com/samwisegamjeee/pytorch-transformers"},{"title":"SambhawDrag/XLNet.jl","url":"https://github.com/SambhawDrag/XLNet.jl"},{"title":"tomgoter/nlp_finalproject","url":"https://github.com/tomgoter/nlp_finalproject"},{"title":"MS-P3/code7","url":"https://github.com/MS-P3/code7/tree/main/xlnet"},{"title":"zaradana/Fast_BERT","url":"https://github.com/zaradana/Fast_BERT"},{"title":"jonahwinninghoff/Text-Summarization","url":"https://github.com/jonahwinninghoff/Text-Summarization"},{"title":"listenviolet/XLNet","url":"https://github.com/listenviolet/XLNet"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/glm-130b-an-open-bilingual-pre-trained-model","title":"GLM-130B: An Open Bilingual Pre-trained Model","date":"2022-10-05","rows_on_this_dataset":14,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":21,"samples_ran":5,"samples_unverified":16,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","rows_on_this_dataset":1,"code_links":27,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":24,"samples_ran":10,"samples_unverified":14,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":45,"samples_ran":15,"samples_unverified":30,"pointer_only_for_licence":3,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}