{"url":"/sota/molecular-property-prediction-on","task":{"name":"Molecular Property Prediction","url":"/task/molecular-property-prediction","note":null},"dataset":{"name":"Lipophilicity","url":null},"category":"Miscellaneous","categories":["Graphs","Medical","Methodology","Miscellaneous"],"category_note":null,"description":"Molecular property prediction is the task of predicting the properties of a molecule from its structure.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["RMSE"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"RMSE":"lower"}},"counts":{"rows":13,"rows_with_code":12,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":9},"rows":[{"rank_in_archive_order":1,"model":"Uni-Mol","metrics":{"RMSE":"0.603"},"uses_additional_data":true,"paper_date":"2022-09-08","paper":"/paper/uni-mol-a-universal-3d-molecular","paper_url":"https://chemrxiv.org/engage/chemrxiv/article-details/628e5b4d5d948517f5ce6d72","paper_title":"Uni-Mol: A Universal 3D Molecular Representation Learning Framework","code":"https://github.com/dptech-corp/Uni-Mol","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"SMA","metrics":{"RMSE":"0.609"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/self-guided-masked-autoencoders-for-domain","paper_url":"https://arxiv.org/abs/2402.14789v1","paper_title":"Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning","code":"https://github.com/johnathan-xie/sma","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":7,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"ChemRL-GEM","metrics":{"RMSE":"0.66"},"uses_additional_data":true,"paper_date":"2021-06-11","paper":"/paper/chemrl-gem-geometry-enhanced-molecular","paper_url":"https://arxiv.org/abs/2106.06130v4","paper_title":"ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":4,"model":"D-MPNN","metrics":{"RMSE":"0.683"},"uses_additional_data":true,"paper_date":"2019-04-02","paper":"/paper/are-learned-molecular-representations-ready","paper_url":"https://arxiv.org/abs/1904.01561v5","paper_title":"Analyzing Learned Molecular Representations for Property Prediction","code":"https://github.com/swansonk14/chemprop","n_code_links":4,"syntology":{"n_ran":3,"n_unverified":12,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"SPMM","metrics":{"RMSE":"0.706"},"uses_additional_data":false,"paper_date":"2022-11-19","paper":"/paper/molecular-structure-property-co-trained","paper_url":"https://arxiv.org/abs/2211.10590v4","paper_title":"Bidirectional Generation of Structure and Properties Through a Single Molecular Foundation Model","code":"https://github.com/jinhojsk515/SPMM","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"PretrainGNN","metrics":{"RMSE":"0.739"},"uses_additional_data":true,"paper_date":"2019-05-29","paper":"/paper/pre-training-graph-neural-networks","paper_url":"https://arxiv.org/abs/1905.12265v3","paper_title":"Strategies for Pre-training Graph Neural Networks","code":"https://github.com/snap-stanford/pretrain-gnns","n_code_links":11,"syntology":{"n_ran":10,"n_unverified":4,"n_samples":14,"n_pointer_only_licence":2}},{"rank_in_archive_order":7,"model":"ChemBFN","metrics":{"RMSE":"0.746"},"uses_additional_data":false,"paper_date":"2024-07-28","paper":"/paper/a-bayesian-flow-network-framework-for","paper_url":"https://arxiv.org/abs/2407.20294v2","paper_title":"A Bayesian Flow Network Framework for Chemistry Tasks","code":"https://github.com/Augus1999/bayesian-flow-network-for-chemistry","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"S-CGIB","metrics":{"RMSE":"0.762±0.042"},"uses_additional_data":false,"paper_date":"2025-02-20","paper":"/paper/pre-training-graph-neural-networks-on","paper_url":"https://arxiv.org/abs/2412.15589","paper_title":"Pre-training Graph Neural Networks on Molecules by Using Subgraph-Conditioned Graph Information Bottleneck","code":"https://github.com/NSLab-CUK/S-CGIB","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"ChemBERTa-2 (MTR-77M)","metrics":{"RMSE":"0.798"},"uses_additional_data":true,"paper_date":"2022-09-05","paper":"/paper/chemberta-2-towards-chemical-foundation","paper_url":"https://arxiv.org/abs/2209.01712v1","paper_title":"ChemBERTa-2: Towards Chemical Foundation Models","code":"https://github.com/seyonechithrananda/bert-loves-chemistry","n_code_links":2,"syntology":null},{"rank_in_archive_order":10,"model":"N-GramRF","metrics":{"RMSE":"0.812"},"uses_additional_data":true,"paper_date":"2018-06-24","paper":"/paper/n-gram-graph-a-novel-molecule-representation","paper_url":"https://arxiv.org/abs/1806.09206v2","paper_title":"N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules","code":"https://github.com/chao1224/n_gram_graph","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"GROVER (base)","metrics":{"RMSE":"0.817"},"uses_additional_data":true,"paper_date":"2020-06-18","paper":"/paper/grover-self-supervised-message-passing","paper_url":"https://arxiv.org/abs/2007.02835v2","paper_title":"Self-Supervised Graph Transformer on Large-Scale Molecular Data","code":"https://github.com/deepchem/deepchem","n_code_links":3,"syntology":null},{"rank_in_archive_order":12,"model":"GROVER (large)","metrics":{"RMSE":"0.823"},"uses_additional_data":true,"paper_date":"2020-06-18","paper":"/paper/grover-self-supervised-message-passing","paper_url":"https://arxiv.org/abs/2007.02835v2","paper_title":"Self-Supervised Graph Transformer on Large-Scale Molecular Data","code":"https://github.com/deepchem/deepchem","n_code_links":3,"syntology":null},{"rank_in_archive_order":13,"model":"N-GramXGB","metrics":{"RMSE":"2.072"},"uses_additional_data":true,"paper_date":"2018-06-24","paper":"/paper/n-gram-graph-a-novel-molecule-representation","paper_url":"https://arxiv.org/abs/1806.09206v2","paper_title":"N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules","code":"https://github.com/chao1224/n_gram_graph","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":14,"n_samples":14,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":7,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":23,"n_unverified":41,"n_samples":64,"n_pointer_only_licence":2,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":23,"n_unverified":55,"n_samples":78,"n_pointer_only_licence":2,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}