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/PaLM 2-M (1-shot)

PaLM 2-M (1-shot)

Reported on 9 benchmarks across 4 tasks · 1 paper

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

Natural Language Processing9 results

  • Question AnsweringonCOPA
    Accuracy· 2023-05-17
    90
    best: 100 (PaLM 540B (finetuned) )
    PaLM 2 Technical ReportarXiv:2305.10403
  • Question AnsweringonPIQA
    Accuracy· 2023-05-17
    83.2
    best: 90.1 (Unicorn 11B (fine-tuned))
    PaLM 2 Technical ReportarXiv:2305.10403
  • Question AnsweringonBoolQ
    Accuracy· 2023-05-17
    88.6
    best: 99.87 (Mistral-Nemo 12B (HPT))
    PaLM 2 Technical ReportarXiv:2305.10403
  • Question AnsweringonOpenBookQA
    Accuracy· 2023-05-17
    56.2
    best: 95.9 (GPT-4 + knowledge base)
    PaLM 2 Technical ReportarXiv:2305.10403
  • Common Sense ReasoningonWinoGrande
    Accuracy· 2023-05-17
    79.2
    best: 96.1 (ST-MoE-32B 269B (fine-tuned))
    PaLM 2 Technical ReportarXiv:2305.10403
  • Common Sense ReasoningonARC (Challenge)
    Accuracy· 2023-05-17
    64.9
    best: 96.4 (GPT-4 (few-shot, k=25))
    PaLM 2 Technical ReportarXiv:2305.10403
  • Common Sense ReasoningonARC (Easy)
    Accuracy· 2023-05-17
    88
    best: 95.2 (ST-MoE-32B 269B (fine-tuned))
    PaLM 2 Technical ReportarXiv:2305.10403
  • Coreference ResolutiononWinograd Schema Challenge
    Accuracy· 2023-05-17
    88.1
    best: 100 (PaLM 540B (fine-tuned))
    PaLM 2 Technical ReportarXiv:2305.10403
  • Sentence CompletiononHellaSwag
    Accuracy· 2023-05-17
    86.7
    best: 96.1 (CompassMTL 567M with Tailor)
    PaLM 2 Technical ReportarXiv:2305.10403