Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MolT5-base

MolT5-base

Reported on 21 benchmarks across 3 tasks · 2 papers

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical20 results

Drug DiscoveryonChEBI-20
BLEU· 2022-04-25
76.9
best: 92.6 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Drug DiscoveryonChEBI-20
Exact Match· 2022-04-25
8.1
best: 53.3 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Drug DiscoveryonChEBI-20
Frechet ChemNet Distance (FCD)· 2022-04-25
2.18
best: 2.49 (MolT5-small)
Translation between Molecules and Natural Language arXiv:2204.11817
Drug DiscoveryonChEBI-20
Levenshtein· 2022-04-25
24.458
best: 28.54 (Text+Chem T5 small)
Translation between Molecules and Natural Language arXiv:2204.11817
Drug DiscoveryonChEBI-20
MACCS FTS· 2022-04-25
72.1
best: 97.3 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Drug DiscoveryonChEBI-20
Morgan FTS· 2022-04-25
52.9
best: 93.1 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Drug DiscoveryonChEBI-20
Parameter Count· 2022-04-25
220000000
best: 770000000 (MolT5-Large)
Translation between Molecules and Natural Language arXiv:2204.11817
Drug DiscoveryonChEBI-20
RDK FTS· 2022-04-25
58.8
best: 95 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Drug DiscoveryonChEBI-20
Text2Mol· 2022-04-25
49.6
best: 59.3 (MolReGPT (GPT-4-0413))
Translation between Molecules and Natural Language arXiv:2204.11817
Drug DiscoveryonChEBI-20
Validity· 2022-04-25
77.2
best: 100 (BioT5+)
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
BLEU· 2022-04-25
76.9
best: 92.6 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
Exact Match· 2022-04-25
8.1
best: 53.3 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
Frechet ChemNet Distance (FCD)· 2022-04-25
2.18
best: 2.49 (MolT5-small)
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
Levenshtein· 2022-04-25
24.458
best: 28.54 (Text+Chem T5 small)
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
MACCS FTS· 2022-04-25
72.1
best: 97.3 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
Morgan FTS· 2022-04-25
52.9
best: 93.1 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
Parameter Count· 2022-04-25
220000000
best: 770000000 (MolT5-Large)
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
RDK FTS· 2022-04-25
58.8
best: 95 (LDMol)
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
Text2Mol· 2022-04-25
49.6
best: 59.3 (MolReGPT (GPT-4-0413))
Translation between Molecules and Natural Language arXiv:2204.11817
Text-based de novo Molecule GenerationonChEBI-20
Validity· 2022-04-25
77.2
best: 100 (BioT5+)
Translation between Molecules and Natural Language arXiv:2204.11817

Natural Language Processing1 result

Description-guided molecule generationonTOMG-Bench
wAcc· 2024-12-19
1.3
best: 35.92 (Claude-3.5)
TOMG-Bench: Evaluating LLMs on Text-based Open Molecule Generation arXiv:2412.14642