TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Mol2Lang-VLM

Mol2Lang-VLM

Reported on 13 benchmarks across 1 task

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

Medical13 results

  • Molecule CaptioningonChEBI-20
    BLEU-2
    61.2
    best: 73.2 (Mol-LLM (Mistral-Instruct-v0.2))
  • Molecule CaptioningonChEBI-20
    BLEU-4
    52.7
    best: 60.8 (MolReFlect)
  • Molecule CaptioningonChEBI-20
    METEOR
    63.3
    best: 68.1 (BioT5+)
  • Molecule CaptioningonChEBI-20
    ROUGE-1
    67.4
    best: 71 (BioT5+)
  • Molecule CaptioningonChEBI-20
    ROUGE-2
    53.2
    best: 61.8 (XMolCap)
  • Molecule CaptioningonChEBI-20
    ROUGE-L
    61.4
    best: 65.3 (PEIT-GEN)
  • Molecule CaptioningonChEBI-20
    Text2Mol
    59.8
    best: 60.3 (BioT5)
  • Molecule CaptioningonL+M-24
    BLEU-2
    77.7
  • Molecule CaptioningonL+M-24
    BLEU-4
    56.3
  • Molecule CaptioningonL+M-24
    METEOR
    74.1
    best: 77.45 (Nach0)
  • Molecule CaptioningonL+M-24
    ROUGE-1
    78.6
    best: 80.06 (Nach0)
  • Molecule CaptioningonL+M-24
    ROUGE-2
    59.1
    best: 60.17 (Nach0)
  • Molecule CaptioningonL+M-24
    ROUGE-L
    56.5
    best: 57.5 (Nach0)