{"url":"/dataset/qm8","name":"QM8","full_name":null,"description_markdown":"QM8 dataset is a collection of molecular data used for studying quantum mechanical calculations of electronic spectra and excited state energy of small molecules. The QM8 dataset consists of approximately 7,165 molecules. These molecules are a subset of the GDB-13 database, which contains nearly 1 billion stable and synthetically accessible organic molecules. The subset includes all molecules with up to 23 atoms, including 7 heavy atoms (C, N, O, and S).","description_withheld":null,"homepage":"http://quantum-machine.org/datasets/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[{"name":"Molecular Property Prediction","url":"/task/molecular-property-prediction","datasets_with_task":"/datasets/task/molecular-property-prediction"}],"languages":[],"variants":["QM8"],"data_loaders":[],"num_papers_in_archive":6,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/molecular-property-prediction-on-qm8","task":"Molecular Property Prediction","dataset_variant":"QM8","rows":8,"metrics":["MAE"],"first_row_in_archive_order":{"model":"Uni-Mol","paper":"/paper/uni-mol-a-universal-3d-molecular","metrics":{"MAE":"0.0156"},"code_links":[{"title":"dptech-corp/Uni-Mol","url":"https://github.com/dptech-corp/Uni-Mol"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/uni-mol-a-universal-3d-molecular","title":"Uni-Mol: A Universal 3D Molecular Representation Learning Framework","date":"2022-09-08","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/chemrl-gem-geometry-enhanced-molecular","title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","date":"2021-06-11","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/grover-self-supervised-message-passing","title":"Self-Supervised Graph Transformer on Large-Scale Molecular Data","date":"2020-06-18","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/pre-training-graph-neural-networks","title":"Strategies for Pre-training Graph Neural Networks","date":"2019-05-29","rows_on_this_dataset":1,"code_links":11,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":10,"samples_unverified":4,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/are-learned-molecular-representations-ready","title":"Analyzing Learned Molecular Representations for Property Prediction","date":"2019-04-02","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":3,"samples_unverified":12,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/n-gram-graph-a-novel-molecule-representation","title":"N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules","date":"2018-06-24","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"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":3,"samples_harvested":43,"samples_ran":13,"samples_unverified":30,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":1,"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."}