{"url":"/dataset/nas-bench-101","name":"NAS-Bench-101","full_name":null,"description_markdown":"**NAS-Bench-101** is the first public architecture dataset for NAS research. To build NASBench-101, the authors carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional\r\narchitectures. The authors trained and evaluated all of these architectures multiple times on CIFAR-10 and compiled the results into a large dataset of over 5 million trained models. This allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the precomputed dataset. \r\n\r\nSource: [NAS-Bench-101: Towards Reproducible Neural Architecture Search](/paper/nas-bench-101-towards-reproducible-neural)","description_withheld":null,"homepage":"https://github.com/google-research/nasbench","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/nas-bench-101-towards-reproducible-neural","title":"NAS-Bench-101: Towards Reproducible Neural Architecture Search","first_author":"Chris Ying","url":null},"license":{"name":"Apache-2.0","url":"https://github.com/google-research/nasbench/blob/master/LICENSE"},"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"AutoML","url":"/task/automl","datasets_with_task":"/datasets/task/automl"},{"name":"Neural Architecture Search","url":"/task/architecture-search","datasets_with_task":"/datasets/task/architecture-search"},{"name":"Hyperparameter Optimization","url":"/task/hyperparameter-optimization","datasets_with_task":"/datasets/task/hyperparameter-optimization"}],"languages":[],"variants":["NAS-Bench-101"],"data_loaders":[{"repo":"https://github.com/google-research/nasbench","url":"https://github.com/google-research/nasbench","frameworks":["tf"]}],"num_papers_in_archive":152,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/neural-architecture-search-on-nas-bench-101","task":"Neural Architecture Search","dataset_variant":"NAS-Bench-101","rows":5,"metrics":["Accuracy (%)","Spearman Correlation"],"first_row_in_archive_order":{"model":"DiNAS","paper":"/paper/multi-conditioned-graph-diffusion-for-neural","metrics":{"Accuracy (%)":"94.98%"},"code_links":[{"title":"rohanasthana/dinas","url":"https://github.com/rohanasthana/dinas"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/multi-conditioned-graph-diffusion-for-neural","title":"Multi-conditioned Graph Diffusion for Neural Architecture Search","date":"2024-03-09","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":7,"samples_ran":4,"samples_unverified":3,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/layernas-neural-architecture-search-in","title":"LayerNAS: Neural Architecture Search in Polynomial Complexity","date":"2023-04-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/improving-neural-architecture-search-by","title":"Improving Neural Architecture Search by Mixing a FireFly algorithm with a Training Free Evaluation","date":"2022-07-18","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/generic-neural-architecture-search-via","title":"Generic Neural Architecture Search via Regression","date":"2021-08-04","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"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":10,"samples_ran":7,"samples_unverified":3,"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."}