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 (few-shot, k=3)

OPT 66B (few-shot, k=3)

Reported on 12 benchmarks across 3 tasks · 1 paper · 1 SOTA

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

Natural Language Processing8 results

  • Question AnsweringonBIG-bench (Movie Recommendation)
    Accuracy· 2023-03-30
    91.2
    best: 94.4 (PaLM 2 (few-shot, k=3, CoT))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Question AnsweringonBIG-bench (Navigate)
    Accuracy· 2023-03-30
    42
    best: 91.2 (PaLM 2 (few-shot, k=3, CoT))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Question AnsweringonBIG-bench (Ruin Names)
    Accuracy· 2023-03-30
    52.8
    best: 90 (PaLM 2 (few-shot, k=3, Direct))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Question AnsweringonBIG-bench (Hyperbaton)
    Accuracy· 2023-03-30
    91.6
    best: 92 (Bloomberg GPT (few-shot, k=3))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Common Sense ReasoningonBIG-bench (Causal Judgment)
    Accuracy· 2023-03-30
    51.87
    best: 62 (PaLM 2 (few-shot, k=3, Direct))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Common Sense ReasoningonBIG-bench (Disambiguation QA)
    Accuracy· 2023-03-30
    40.4
    best: 78.8 (PaLM 2 (few-shot, k=3, Direct))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Common Sense ReasoningonBIG-bench (Sports Understanding)
    Accuracy· 2023-03-30
    54.4
    best: 98 (PaLM 2(few-shot, k=3, CoT))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Common Sense ReasoningonBIG-bench (Date Understanding)
    Accuracy· 2023-03-30
    49.6
    best: 91.2 (PaLM 2 (few-shot, k=3, CoT))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564

Methodology4 results

  • Logical ReasoningonBIG-bench (Formal Fallacies Syllogisms Negation)
    Accuracy· 2023-03-30
    54
    best: 64.8 (PaLM 2 (few-shot, k=3, Direct))
    SOTA
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Logical ReasoningonBIG-bench (Penguins In A Table)
    Accuracy· 2023-03-30
    28.08
    best: 84.9 (PaLM 2 (few-shot, k=3, CoT))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Logical ReasoningonBIG-bench (Temporal Sequences)
    Accuracy· 2023-03-30
    23.6
    best: 100 (PaLM 2 (few-shot, k=3, CoT))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564
  • Logical ReasoningonBIG-bench (Reasoning About Colored Objects)
    Accuracy· 2023-03-30
    31.2
    best: 91.2 (PaLM 2 (few-shot, k=3, CoT))
    BloombergGPT: A Large Language Model for FinancearXiv:2303.17564