MoMu+MolT5-Large

Reported on 4 benchmarks across 1 task · 1 paper · 2 SOTA

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

Medical4 results

Molecule CaptioningonChEBI-20
BLEU-2· 2022-09-12
59.9
best: 73.2 (Mol-LLM (Mistral-Instruct-v0.2))
SOTA
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language arXiv:2209.05481
Molecule CaptioningonChEBI-20
BLEU-4· 2022-09-12
51.5
best: 60.8 (MolReFlect)
SOTA
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language arXiv:2209.05481
Molecule CaptioningonChEBI-20
METEOR· 2022-09-12
59.7
best: 68.1 (BioT5+)
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language arXiv:2209.05481
Molecule CaptioningonChEBI-20
Text2Mol· 2022-09-12
58.2
best: 60.3 (BioT5)
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language arXiv:2209.05481