[]() | | 73.2 | | | | | | | Mol-LLM (Mistral-Instruct-v0.2) | |
[]() | | 72.70 | | | | | | | Mol-LLM (LLaMA2-Chat) | |
MolReFlect: Towards Fine-grained In-Context Alignment between Molecules and Texts | | 67.6 | 60.8 | 68.0 | 70.3 | 57.1 | 64.4 | | MolReFlect | 2024-11-22 |
BioT5+: Towards Generalized Biological Understanding with IUPAC Integration and Multi-task Tuning | ✓ Link | 66.6 | 59.1 | 68.1 | 71.0 | 58.4 | 65.0 | | BioT5+ | 2024-02-27 |
BioT5: Enriching Cross-modal Integration in Biology with Chemical Knowledge and Natural Language Associations | ✓ Link | 63.5 | 55.6 | 65.6 | 69.2 | 55.9 | 63.3 | 60.3 | BioT5 | 2023-10-11 |
Unifying Molecular and Textual Representations via Multi-task Language Modelling | ✓ Link | 62.5 | 54.2 | 64.8 | 68.2 | 54.3 | 62.2 | | Text+Chem T5-augm-Base | 2023-01-29 |
XMolCap: Advancing Molecular Captioning through Multimodal Fusion and Explainable Graph Neural Networks | ✓ Link | 62.0 | 53.8 | 67.8 | 53.9 | 61.8 | 63.8 | | XMolCap | 2025-05-23 |
MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter | ✓ Link | 62.0 | 53.1 | 65.1 | 68.1 | 53.7 | 61.8 | | MolCA, Galac1.3B | 2023-10-19 |
MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter | ✓ Link | 61.6 | 52.9 | 63.9 | 67.4 | 53.3 | 61.5 | | MolCA, Galac125M | 2023-10-19 |
Mol2Lang-VLM: Vision- and Text-Guided Generative Pre-trained Language Models for Advancing Molecule Captioning through Multimodal Fusion | ✓ Link | 61.2 | 52.7 | 63.3 | 67.4 | 53.2 | 61.4 | 59.8 | Mol2Lang-VLM | 2024-08-15 |
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective | ✓ Link | 60.7 | 52.5 | 61.0 | 63.4 | 47.6 | 56.2 | 58.5 | MolReGPT (GPT-4-0314) | 2023-06-11 |
Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language | ✓ Link | 60.2 | 52.1 | 63.4 | 65.5 | 51.2 | 59.8 | 59.7 | LaMolT5-Large | 2025-02-10 |
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language | ✓ Link | 59.9 | 51.5 | 59.7 | | | | 58.2 | MoMu+MolT5-Large | 2022-09-12 |
Property Enhanced Instruction Tuning for Multi-task Molecule Generation with Large Language Models | ✓ Link | 59.8 | 53.4 | 67.6 | 70.0 | 58.2 | 65.3 | | PEIT-GEN | 2024-12-24 |
Translation between Molecules and Natural Language | ✓ Link | 59.4 | 50.8 | 61.4 | 65.4 | 51.0 | 59.4 | 58.2 | MolT5-Large | 2022-04-25 |
MolXPT: Wrapping Molecules with Text for Generative Pre-training | ✓ Link | 59.4 | 50.5 | 62.6 | 66 | 51.1 | 59.7 | 59.4 | MolXPT | 2023-05-18 |
Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization | | 58.7 | 51.5 | 61.7 | 62.7 | 48.7 | 57.1 | | Mol-LLM (SELFIES) | 2025-02-05 |
MolFM: A Multimodal Molecular Foundation Model | ✓ Link | 58.5 | 49.8 | 60.7 | 65.3 | 50.8 | 59.4 | 57.6 | MolFM-Base | 2023-06-06 |
Unifying Molecular and Textual Representations via Multi-task Language Modelling | ✓ Link | 58 | 49 | 60.4 | 64.7 | 49.8 | 58.6 | | Text+Chem T5-Base | 2023-01-29 |
Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language | ✓ Link | 57.4 | 48.5 | 59.6 | 63.4 | 47.8 | 56.4 | 59.9 | LaMolT5-Base | 2025-02-10 |
Empowering Molecule Discovery for Molecule-Caption Translation with Large Language Models: A ChatGPT Perspective | ✓ Link | 56.5 | 48.2 | 62.3 | 45.0 | 54.3 | 58.5 | 56.0 | MolReGPT (GPT-3.5-turbo) | 2023-06-11 |
Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization | | 56.0 | 49.0 | 59.3 | 52.4 | 37.0 | 46.7 | | Mol-LLM | 2025-02-05 |
Unifying Molecular and Textual Representations via Multi-task Language Modelling | ✓ Link | 56.0 | 47.0 | 58.8 | 63.8 | 48.8 | 58 | | Text+Chem T5-augm-Small | 2023-01-29 |
Unifying Molecular and Textual Representations via Multi-task Language Modelling | ✓ Link | 55.3 | 46.2 | 58.3 | 63.3 | 48.1 | 57.4 | | Text+Chem T5-Small | 2023-01-29 |
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language | ✓ Link | 54.9 | 46.2 | 57.6 | | | | 55.8 | MoMu+MolT5-Base | 2022-09-12 |
MolFM: A Multimodal Molecular Foundation Model | ✓ Link | 54.2 | 45.2 | 56.4 | 62.3 | 46.9 | 56.2 | 55.7 | MolFM-Small | 2023-06-06 |
Graph-based Molecular Representation Learning | ✓ Link | 54.2 | 43.9 | 58.5 | 61.7 | 46.6 | 56.1 | | GAMIC (Mistral) | 2022-07-08 |
Translation between Molecules and Natural Language | ✓ Link | 54.0 | 45.7 | 56.9 | 63.4 | 48.5 | 57.8 | 54.7 | MolT5-Base | 2022-04-25 |
Automatic Annotation Augmentation Boosts Translation between Molecules and Natural Language | ✓ Link | 53.9 | 44.6 | 56.6 | 62.0 | 46.9 | 56.3 | 58.8 | LaMolT5-Small | 2025-02-10 |
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language | ✓ Link | 53.2 | 44.5 | 55.7 | | | | 55.3 | MoMu+MolT5-Small | 2022-09-12 |
Translation between Molecules and Natural Language | ✓ Link | 51.9 | 43.6 | 55.1 | 62.0 | 46.9 | 56.3 | 54.0 | MolT5-Small | 2022-04-25 |
InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery | ✓ Link | 47.5 | 37.1 | 50.9 | 56.6 | 39.4 | 50.2 | | InstructMol-GS | 2023-11-27 |
InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery | ✓ Link | 46.6 | 36.5 | 49.1 | 54.7 | 36.5 | 47.9 | | InstructMol-G | 2023-11-27 |