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/MolReGPT (GPT-3.5-turbo)

MolReGPT (GPT-3.5-turbo)

Reported on 25 benchmarks across 3 tasks · 1 paper

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

Medical25 results

Drug DiscoveryonChEBI-20
BLEU· 2023-06-11
79
best: 92.6 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Drug DiscoveryonChEBI-20
Exact Match· 2023-06-11
13.9
best: 53.3 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Drug DiscoveryonChEBI-20
Frechet ChemNet Distance (FCD)· 2023-06-11
0.57
best: 2.49 (MolT5-small)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Drug DiscoveryonChEBI-20
Levenshtein· 2023-06-11
24.91
best: 28.54 (Text+Chem T5 small)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Drug DiscoveryonChEBI-20
MACCS FTS· 2023-06-11
84.7
best: 97.3 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Drug DiscoveryonChEBI-20
Morgan FTS· 2023-06-11
62.4
best: 93.1 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Drug DiscoveryonChEBI-20
RDK FTS· 2023-06-11
70.8
best: 95 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Drug DiscoveryonChEBI-20
Text2Mol· 2023-06-11
57.1
best: 59.3 (MolReGPT (GPT-4-0413))
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Drug DiscoveryonChEBI-20
Validity· 2023-06-11
88.7
best: 100 (BioT5+)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Molecule CaptioningonChEBI-20
BLEU-2· 2023-06-11
56.5
best: 73.2 (Mol-LLM (Mistral-Instruct-v0.2))
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Molecule CaptioningonChEBI-20
BLEU-4· 2023-06-11
48.2
best: 60.8 (MolReFlect)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Molecule CaptioningonChEBI-20
METEOR· 2023-06-11
62.3
best: 68.1 (BioT5+)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Molecule CaptioningonChEBI-20
ROUGE-1· 2023-06-11
45
best: 71 (BioT5+)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Molecule CaptioningonChEBI-20
ROUGE-2· 2023-06-11
54.3
best: 61.8 (XMolCap)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Molecule CaptioningonChEBI-20
ROUGE-L· 2023-06-11
58.5
best: 65.3 (PEIT-GEN)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Molecule CaptioningonChEBI-20
Text2Mol· 2023-06-11
56
best: 60.3 (BioT5)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Text-based de novo Molecule GenerationonChEBI-20
BLEU· 2023-06-11
79
best: 92.6 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Text-based de novo Molecule GenerationonChEBI-20
Exact Match· 2023-06-11
13.9
best: 53.3 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Text-based de novo Molecule GenerationonChEBI-20
Frechet ChemNet Distance (FCD)· 2023-06-11
0.57
best: 2.49 (MolT5-small)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Text-based de novo Molecule GenerationonChEBI-20
Levenshtein· 2023-06-11
24.91
best: 28.54 (Text+Chem T5 small)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Text-based de novo Molecule GenerationonChEBI-20
MACCS FTS· 2023-06-11
84.7
best: 97.3 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Text-based de novo Molecule GenerationonChEBI-20
Morgan FTS· 2023-06-11
62.4
best: 93.1 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Text-based de novo Molecule GenerationonChEBI-20
RDK FTS· 2023-06-11
70.8
best: 95 (LDMol)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Text-based de novo Molecule GenerationonChEBI-20
Text2Mol· 2023-06-11
57.1
best: 59.3 (MolReGPT (GPT-4-0413))
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615
Text-based de novo Molecule GenerationonChEBI-20
Validity· 2023-06-11
88.7
best: 100 (BioT5+)
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective arXiv:2306.06615