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/OpenMath-CodeLlama-70B (w/ code)

OpenMath-CodeLlama-70B (w/ code)

Reported on 22 benchmarks across 5 tasks · 1 paper · 4 SOTA

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

Knowledge Base10 results

  • Mathematical Question AnsweringonMAWPS
    Accuracy (%)· uses extra data· 2024-02-15
    95.7
    SOTA
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Mathematical ReasoningonMAWPS
    Accuracy (%)· uses extra data· 2024-02-15
    95.7
    SOTA
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Mathematical Question AnsweringonMATH
    Accuracy· uses extra data· 2024-02-15
    50.7
    best: 89.7 (Gemini 2.0 Flash Experimental)
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Mathematical Question AnsweringonMATH
    Parameters (Billions)· uses extra data· 2024-02-15
    70
    best: 540 (Minerva 540B)
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Mathematical Question AnsweringonASDiv-A
    Execution Accuracy· uses extra data· 2024-02-15
    84.7
    best: 91 (ATHENA (roberta-large))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Mathematical Question AnsweringonSVAMP
    Execution Accuracy· uses extra data· 2024-02-15
    87.8
    best: 93.9 (GPT-4 (Teaching-Inspired))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Mathematical ReasoningonMATH
    Accuracy· uses extra data· 2024-02-15
    50.7
    best: 89.7 (Gemini 2.0 Flash Experimental)
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Mathematical ReasoningonMATH
    Parameters (Billions)· uses extra data· 2024-02-15
    70
    best: 540 (Minerva 540B)
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Mathematical ReasoningonASDiv-A
    Execution Accuracy· uses extra data· 2024-02-15
    84.7
    best: 91 (ATHENA (roberta-large))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Mathematical ReasoningonSVAMP
    Execution Accuracy· uses extra data· 2024-02-15
    87.8
    best: 93.9 (GPT-4 (Teaching-Inspired))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176

Reasoning7 results

  • Math Word Problem SolvingonMAWPS
    Accuracy (%)· uses extra data· 2024-02-15
    95.7
    SOTA
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Math Word Problem SolvingonMATH
    Accuracy· uses extra data· 2024-02-15
    50.7
    best: 89.7 (Gemini 2.0 Flash Experimental)
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Math Word Problem SolvingonMATH
    Parameters (Billions)· uses extra data· 2024-02-15
    70
    best: 540 (Minerva 540B)
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Math Word Problem SolvingonASDiv-A
    Execution Accuracy· uses extra data· 2024-02-15
    84.7
    best: 91 (ATHENA (roberta-large))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Math Word Problem SolvingonSVAMP
    Execution Accuracy· uses extra data· 2024-02-15
    87.8
    best: 93.9 (GPT-4 (Teaching-Inspired))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Arithmetic ReasoningonGSM8K
    Accuracy· uses extra data· 2024-02-15
    84.6
    best: 97.72 (Claude 3.5 Sonnet (HPT))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Arithmetic ReasoningonGSM8K
    Parameters (Billion)· uses extra data· 2024-02-15
    70
    best: 540 (PaLM 540B (Self Improvement, Self Consistency))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176

Natural Language Processing5 results

  • Question AnsweringonMAWPS
    Accuracy (%)· uses extra data· 2024-02-15
    95.7
    SOTA
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Question AnsweringonMATH
    Accuracy· uses extra data· 2024-02-15
    50.7
    best: 89.7 (Gemini 2.0 Flash Experimental)
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Question AnsweringonMATH
    Parameters (Billions)· uses extra data· 2024-02-15
    70
    best: 540 (Minerva 540B)
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Question AnsweringonASDiv-A
    Execution Accuracy· uses extra data· 2024-02-15
    84.7
    best: 91 (ATHENA (roberta-large))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176
  • Question AnsweringonSVAMP
    Execution Accuracy· uses extra data· 2024-02-15
    87.8
    best: 93.9 (GPT-4 (Teaching-Inspired))
    OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning DatasetarXiv:2402.10176