List your company
ResearchFormerly WizWand

Binary Classification on MoleculeNet BBBP (test)

0.8ROC AUCMolXPT
0.516080.589790.66350.73721Sep 5, 2022Apr 17, 2023Nov 27, 2023Jul 9, 2024Feb 18, 2025Sep 30, 2025May 13, 2026
Updated 5mo ago

Evaluation results

MethodLinks
MolXPTModel Category=Single-task Specialist Models2024.020.8
BioT5Model Category=Single-task Specialist Models2024.020.777
SPD-Sheaf2026.040.774
BioT5+Model Category=LLM-based Generalist Models2024.020.765
ChemBERTa-2Pre-training Task=MTR, Pre-training Dataset Size=5M, Evaluation Protocol=Fine-tuned2022.090.742
ChemBERTa-2Pre-training strategy=MTR, Pre-training size=5M2026.050.742
MolCLRModel Category=Single-task Specialist Models2024.020.738
SMPT2026.040.734
ChemBERTa-2Pre-training Task=MTR, Pre-training Dataset Size=10M, Evaluation Protocol=Fine-tuned2022.090.733
ChemBERTa-2Pre-training strategy=MTR, Pre-training size=10M2026.050.733
Uni-MolModel Category=Single-task Specialist Models2024.020.729
MolFMModel Category=Single-task Specialist Models2024.020.729
Uni-Mol2026.040.729
ChemBERTa-2Pre-training Task=MTR, Pre-training Dataset Size=77M, Evaluation Protocol=Fine-tuned2022.090.728
Mol-GDL2026.040.728
ChemBERTa-2Pre-training strategy=MTR, Pre-training size=77M2026.050.728
GraphMVP-CModel Category=Single-task Specialist Models2024.020.724
GEMModel Category=Single-task Specialist Models2024.020.724
GraphMVP2026.040.724
GEM2026.040.724
MolCLR2026.040.722
Chem-GMNetPre-training strategy=scratch, k=82026.050.722
EGNN2026.040.721
RFEvaluation Protocol=Fine-tuned2022.090.7194
Random ForestPre-training strategy=None2026.050.719
D-MPNN2026.040.71
Chem-GMNetPre-training strategy=scratch, k=102026.050.71
SchNet2026.040.708
MGSSLModel Category=Single-task Specialist Models2024.020.705
MoMuModel Category=Single-task Specialist Models2024.020.705
ChemBERTa-2Pre-training Task=MLM, Pre-training Dataset Size=5M, Evaluation Protocol=Fine-tuned2022.090.701
ChemBERTa-2Pre-training strategy=MLM, Pre-training size=5M2026.050.701
InstructMol-GS-6.9BModel Category=LLM-based Generalist Models2024.020.7
GROVEModel Variant=base2026.040.7
ChemBERTa-2Pre-training Task=MLM, Pre-training Dataset Size=77M, Evaluation Protocol=Fine-tuned2022.090.698
ChemBERTa-2Pre-training strategy=MLM, Pre-training size=77M2026.050.698
Chem-GMNetPre-training strategy=MLM, Pre-training size=10M2026.050.698
D-MPNNEvaluation Protocol=Fine-tuned2022.090.697
GraphCLModel Category=Single-task Specialist Models2024.020.697
N-GramClassifier=RF2026.040.697
D-MPNN (Chemprop)Pre-training strategy=None2026.050.697
ChemBERTa-2Pre-training Task=MLM, Pre-training Dataset Size=10M, Evaluation Protocol=Fine-tuned2022.090.696
ChemBERTa-2Pre-training strategy=MLM, Pre-training size=10M2026.050.696
GROVEModel Variant=large2026.040.695
N-GramClassifier=XGB2026.040.691
PretrainGNN2026.040.687
GCNEvaluation Protocol=Fine-tuned2022.090.676
GCNPre-training strategy=None2026.050.676
KV-PLMModel Category=Single-task Specialist Models2024.020.669
AttentiveFP2026.040.663
Galactica-120BModel Category=LLM-based Generalist Models2024.020.661
Llama-2-7B-chatModel Category=LLM-based Generalist Models, tuning=LoRA2024.020.656
ChemBERTa-1Evaluation Protocol=Fine-tuned2022.090.643
ChemBERTa-1Pre-training strategy=MLM2026.050.643
InstructMol-G-6.9BModel Category=LLM-based Generalist Models2024.020.64
Vicuna-v1.3-7BModel Category=LLM-based Generalist Models, tuning=LoRA2024.020.601
Galactica-30BModel Category=LLM-based Generalist Models2024.020.596
Galactica-6.7BModel Category=LLM-based Generalist Models2024.020.535
Vicuna-v1.5-13B-16kModel Category=LLM-based Generalist Models, Shot=4-shot2024.020.527