neulab/gemini-benchmark

Issues

• Double-check filtering of final strings in codegen

  #38 opened 3 months ago by neubig
  0

• Code Generation Evals should parse code from LM response

  #29 opened 10 months ago by manishshettym
  6

• Update paper and re-release

  #33 opened a year ago by neubig
  0

• Re-run with Gemini's safety settings off

  #32 opened a year ago by neubig
  0

• Check results of re-run experiments

  #35 opened a year ago by neubig
  0

• Re-run Mistral Evals w/ official Mistral-Instruct

  #31 opened a year ago by neubig
  0

• Question regarding Mixtral evaluation

  #34 opened a year ago by NielsRogge
  2

• Improve README

  #17 opened a year ago by neubig
  0

• Mathematical Reasoning Checklist

  #11 opened a year ago by neubig
  0

• Instruction Following Checklist

  #14 opened a year ago by neubig
  0

• Code Generation Checklist

  #12 opened a year ago by neubig
  0

• Machine Translation Checklist

  #13 opened a year ago by neubig
  0

• Common-sense QA checklist

  #10 opened a year ago by neubig
  4

• Text understanding checklist

  #9 opened a year ago by neubig
  0