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/OPT 66B (one-shot)

OPT 66B (one-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

  • Reading ComprehensiononRACE
    Accuracy (High)· 2023-03-30
    37.02
    best: 92.6 (ALBERTxxlarge+DUMA(ensemble))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Reading ComprehensiononRACE
    Accuracy (Middle)· 2023-03-30
    47.42
    best: 93.1 (Megatron-BERT (ensemble))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Question AnsweringonCOPA
    Accuracy· 2023-03-30
    86
    best: 100 (PaLM 540B (finetuned) )
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Question AnsweringonOpenBookQA
    Accuracy· 2023-03-30
    58
    best: 95.9 (GPT-4 + knowledge base)
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Common Sense ReasoningonARC (Challenge)
    Accuracy· 2023-03-30
    44.54
    best: 96.4 (GPT-4 (few-shot, k=25))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Natural Language InferenceonANLI test
    A1· 2023-03-30
    33.1
    best: 81.8 (T5-3B (explanation prompting))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Natural Language InferenceonANLI test
    A2· 2023-03-30
    34.2
    best: 72.5 (T5-3B (explanation prompting))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Natural Language InferenceonANLI test
    A3· 2023-03-30
    34.92
    best: 74.8 (T5-3B (explanation prompting))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Natural Language InferenceonCommitmentBank
    Accuracy· 2023-03-30
    44.64
    best: 100 (PaLM 540B (finetuned))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564