AI Paper Atlas

Research map / Benchmarks / Tox21

Tox21 leaderboard

25 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on Tox21. Best ROC-AUC: 85.74 (GEM + APMP, AAAI 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

Tox21 · ROC-AUC

25 papers, each with its best reported number for its own method; higher is better.

#ROC-AUC ↑MethodPaperTopic
185.74GEM + APMP
GEM
Association Pattern-enhanced Molecular Representation Learning
AAAI 2025 · Table 2
Self-supervised and contrastive
284.3GodeBi-level Contrastive Learning for Knowledge-Enhanced Molecule Representations
AAAI 2025 · Table: Performance on six clas
Graph self-supervised learning
381.3MOL-MambaMOL-Mamba: Enhancing Molecular Representation with Structural & Electronic Insights
AAAI 2025 · Table: classification benchmar
Graph self-supervised learning
480.67MolTailor
CHEM-BERT
MolTailor: Tailoring Chemical Molecular Representation to Specific Tasks via Text Prompts
AAAI 2024 · Table 1
Language, safety and interpretability
580.6MIPTMIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction
ICML 2025 · Table 2
Graph self-supervised learning
680.1Ours (Gamma)
Uni-Mol
A probability contrastive learning framework for 3D molecular representation learning
NeurIPS 2024 · Table 1
Recognition and long-tail
779.9GEM + InstructMol
GEM
Instructor-inspired Machine Learning for Robust Molecular Property Prediction
NeurIPS 2024 · Table 3
Recognition and long-tail
879.36TRIDENT (M-M)
MOLFORMER + MolT5
TRIDENT: Tri-Modal Molecular Representation Learning with Taxonomic Annotations and Local Correspondence
NeurIPS 2025 · MoleculeNet results table
Human and embodied modeling
979.2OEPGOmni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learning
ICML 2022 · Table: Downstream test ROC-AUC
Graph self-supervised learning
1078.6L2R-GNNLearning to Reweight for Generalizable Graph Neural Network
AAAI 2024 · Table 1
GNN architectures
15 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.