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/GIT-Mol-caption

GIT-Mol-caption

Reported on 14 benchmarks across 2 tasks · 1 paper

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

Medical14 results

Drug DiscoveryonChEBI-20
BLEU· 2023-08-14
75.6
best: 92.6 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Drug DiscoveryonChEBI-20
Exact Match· 2023-08-14
5.1
best: 53.3 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Drug DiscoveryonChEBI-20
Levenshtein· 2023-08-14
26.315
best: 28.54 (Text+Chem T5 small)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Drug DiscoveryonChEBI-20
MACCS FTS· 2023-08-14
73.8
best: 97.3 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Drug DiscoveryonChEBI-20
Morgan FTS· 2023-08-14
51.9
best: 93.1 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Drug DiscoveryonChEBI-20
RDK FTS· 2023-08-14
58.2
best: 95 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Drug DiscoveryonChEBI-20
Validity· 2023-08-14
92.8
best: 100 (BioT5+)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Text-based de novo Molecule GenerationonChEBI-20
BLEU· 2023-08-14
75.6
best: 92.6 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Text-based de novo Molecule GenerationonChEBI-20
Exact Match· 2023-08-14
5.1
best: 53.3 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Text-based de novo Molecule GenerationonChEBI-20
Levenshtein· 2023-08-14
26.315
best: 28.54 (Text+Chem T5 small)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Text-based de novo Molecule GenerationonChEBI-20
MACCS FTS· 2023-08-14
73.8
best: 97.3 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Text-based de novo Molecule GenerationonChEBI-20
Morgan FTS· 2023-08-14
51.9
best: 93.1 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Text-based de novo Molecule GenerationonChEBI-20
RDK FTS· 2023-08-14
58.2
best: 95 (LDMol)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911
Text-based de novo Molecule GenerationonChEBI-20
Validity· 2023-08-14
92.8
best: 100 (BioT5+)
GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text arXiv:2308.06911