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/Mistral 7B (0-shot)

Mistral 7B (0-shot)

Reported on 5 benchmarks across 3 tasks · 2 papers

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

Natural Language Processing8 results

  • Question AnsweringonPIQA
    Accuracy· 2024-01-08
    82.2
    best: 90.1 (Unicorn 11B (fine-tuned))
    Mixtral of ExpertsarXiv:2401.04088
  • Common Sense ReasoningonWinoGrande
    Accuracy· 2024-01-08
    74.2
    best: 96.1 (ST-MoE-32B 269B (fine-tuned))
    Mixtral of ExpertsarXiv:2401.04088
  • Common Sense ReasoningonARC (Easy)
    Accuracy· 2024-01-08
    80.5
    best: 95.2 (ST-MoE-32B 269B (fine-tuned))
    Mixtral of ExpertsarXiv:2401.04088
  • Question AnsweringonPIQA
    Accuracy· 2023-10-10
    83
    best: 90.1 (Unicorn 11B (fine-tuned))
    Mistral 7BarXiv:2310.06825
  • Common Sense ReasoningonWinoGrande
    Accuracy· 2023-10-10
    75.3
    best: 96.1 (ST-MoE-32B 269B (fine-tuned))
    Mistral 7BarXiv:2310.06825
  • Common Sense ReasoningonARC (Challenge)
    Accuracy· 2023-10-10
    55.5
    best: 96.4 (GPT-4 (few-shot, k=25))
    Mistral 7BarXiv:2310.06825
  • Common Sense ReasoningonARC (Easy)
    Accuracy· 2023-10-10
    80
    best: 95.2 (ST-MoE-32B 269B (fine-tuned))
    Mistral 7BarXiv:2310.06825
  • Sentence CompletiononHellaSwag
    Accuracy· 2023-10-10
    81.3
    best: 96.1 (CompassMTL 567M with Tailor)
    Mistral 7BarXiv:2310.06825