scicode-bench/SciCode

Issues

• Add gpt-4.5 to the leaderboard

  #37 opened 8 months ago by LuigiPagani
  0

• Benchmark o1

  #35 opened 8 months ago by LuigiPagani
  0

• Benchmark Claude Sonnet 3.7

  #36 opened 8 months ago by LuigiPagani
  0

• Improve discoverability of your work on Hugging Face

  #5 opened 9 months ago by NielsRogge
  3

• add new claude-3-5-sonnet-20241022

  #18 opened 9 months ago by Kreijstal
  0

• Add o1 17/12 To the Leaderboard

  #21 opened 9 months ago by LuigiPagani
  2

• One click run

  #6 opened 9 months ago by ofirpress
  2

• Deepseek R1 Evaluation Results?

  #25 opened 9 months ago by jasonzliang
  2

• Ground Truth Code for problems_all.jsonl

  #20 opened 9 months ago by jasonzliang
  2

• o1 models results

  #17 opened a year ago by stalkermustang
  1

• Solution generation skips certain steps?

  #12 opened a year ago by idavidrein
  2

• Request to evaluate the new O1 models by OpenAI (O1-preview and O1-mini)

  #14 opened a year ago by Belzedar94
  2

• Potentially Too Strict Judgement on Calculated Result

  #8 opened a year ago by XuGW-Kevin
  2

• Inquiry on Skipping Specific Problems in SciCode Benchmark

  #1 opened a year ago by HariSeldon0
  1

• Dependency versions for evaluation

  #2 opened a year ago by zrait
  0