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/GEO

GEO

Reported on 12 benchmarks across 4 tasks

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

Knowledge Base6 results

  • Mathematical Question AnsweringonMAWPS
    Accuracy (%)
    85.1
    best: 95.7 (OpenMath-CodeLlama-70B (w/ code))
  • Mathematical Question AnsweringonALG514
    Accuracy (%)
    82.1
    best: 83 (MixedSP)
  • Mathematical Question AnsweringonDRAW-1K
    Accuracy (%)
    62.5
    best: 63.5 (EPT)
  • Mathematical ReasoningonMAWPS
    Accuracy (%)
    85.1
    best: 95.7 (OpenMath-CodeLlama-70B (w/ code))
  • Mathematical ReasoningonALG514
    Accuracy (%)
    82.1
    best: 83 (MixedSP)
  • Mathematical ReasoningonDRAW-1K
    Accuracy (%)
    62.5
    best: 63.5 (EPT)

Natural Language Processing3 results

  • Question AnsweringonMAWPS
    Accuracy (%)
    85.1
    best: 95.7 (OpenMath-CodeLlama-70B (w/ code))
  • Question AnsweringonALG514
    Accuracy (%)
    82.1
    best: 83 (MixedSP)
  • Question AnsweringonDRAW-1K
    Accuracy (%)
    62.5
    best: 63.5 (EPT)

Reasoning3 results

  • Math Word Problem SolvingonMAWPS
    Accuracy (%)
    85.1
    best: 95.7 (OpenMath-CodeLlama-70B (w/ code))
  • Math Word Problem SolvingonALG514
    Accuracy (%)
    82.1
    best: 83 (MixedSP)
  • Math Word Problem SolvingonDRAW-1K
    Accuracy (%)
    62.5
    best: 63.5 (EPT)