Mol-LLM

Reported on 6 benchmarks across 1 task · 1 paper

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

Medical6 results

Molecule CaptioningonChEBI-20
BLEU-2· 2025-02-05
56
best: 73.2 (Mol-LLM (Mistral-Instruct-v0.2))
Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization arXiv:2502.02810
Molecule CaptioningonChEBI-20
BLEU-4· 2025-02-05
49
best: 60.8 (MolReFlect)
Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization arXiv:2502.02810
Molecule CaptioningonChEBI-20
METEOR· 2025-02-05
59.3
best: 68.1 (BioT5+)
Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization arXiv:2502.02810
Molecule CaptioningonChEBI-20
ROUGE-1· 2025-02-05
52.4
best: 71 (BioT5+)
Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization arXiv:2502.02810
Molecule CaptioningonChEBI-20
ROUGE-2· 2025-02-05
37
best: 61.8 (XMolCap)
Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization arXiv:2502.02810
Molecule CaptioningonChEBI-20
ROUGE-L· 2025-02-05
46.7
best: 65.3 (PEIT-GEN)
Mol-LLM: Multimodal Generalist Molecular LLM with Improved Graph Utilization arXiv:2502.02810