OpenLMLab/GAOKAO-Bench

Issues

• 开源人工评分数据集

  #40 opened a month ago by Nefefilibata
  0

• 2024高考评测集

  #39 opened a month ago by cobraheleah
  0

• 分数不一致

  #38 opened 2 months ago by kekezhai
  1

• 论文中温度是0.3，可以分享一下其他值的设置吗，比如top_p，top_k

  #37 opened 3 months ago by jidandan666
  1

• A question about the paper

  #36 opened 4 months ago by endNone
  4

• 是否支持其他开源模型本地调用，不是以apikey方式

  #35 opened 4 months ago by jidandan666
  4

• The evaluation result can't match the paper result

  #33 opened 8 months ago by CoderBak
  3

• Missing Question

  #30 opened 9 months ago by MarigoldTechStriker
  1

• Where are the evaluation results for those two columns?

  #25 opened 9 months ago by zhimin-z
  1

• Solution of "Exception: list index out of range" when run `python choice_bench.py`

  #18 opened 9 months ago by ALLinLLM
  1

• json. decoder.JSONDecodeError: Invalid escape:

  #19 opened 9 months ago by zyy-2001
  3

• Typos in the dataset.

  #20 opened 9 months ago by chengeharrison
  1

• 关于测试题目格式

  #21 opened 9 months ago by jimmyzhang610
  1

• gpt-3.5-turbo 高考得分 在哪？

  #7 opened 9 months ago by bansky-cl
  1

• 有GPT-4的具体实验结果吗

  #28 opened 9 months ago by K1yomi
  2

• 请问1000道主观题都是完全的人工评分吗？涉及到用gpt4来评分吗？

  #23 opened 9 months ago by eyuansu62
  4

• 按照README文档运行Openai Api简单实例，运行choice_bench.py后输出2010-2022_Math_II_MCQs single_choice mkdir: cannot create directory ‘../data/Multiple-choice_Questions/gpt-3.5-turbo_2010-2022_Math_II_MCQs’: File exists 0%| | 0/44 [00:00<?, ?it/s]Exception: Cannot choose from an empty sequence 0%| | 0/44 [00:00<?, ?it/s]Exception: Cannot choose from an empty sequence 0%| | 0/42 [00:00<?, ?it/s]Exception: Cannot choose from an empty sequence 0%| | 0/44 [00:00<?, ?it/s]Exception: Cannot choose from an empty sequence 0%| | 0/44 [00:00<?, ?it/s]Exception: Cannot choose from an empty sequence Exception: Cannot choose from an empty sequence

  #27 opened a year ago by FreshOrangess
  0

• 请问`Gaokao-2023`这个数据集去哪里找呢？

  #26 opened a year ago by zhimin-z
  1

• 请问关于评估过程是0shot评测还是5shot评测？

  #24 opened a year ago by liu904-61
  2

• 这个评测怎么没有排除主观评测

  #22 opened a year ago by eyuansu62
  0

• 有没有gpt4的得分？

  #4 opened a year ago by vsEcho567
  2

• 数学I小错误

  #10 opened a year ago by liyongsea
  2

• 数据收集过程

  #13 opened a year ago by Richar-Du
  1

• 数学题格式

  #11 opened a year ago by liyongsea
  2

• 猪八诶

  #5 opened 2 years ago by sfsdfd62
  0

• Bench 目录下三个 prompt.json 文件中有 <eoa> 错写成 <eoe>

  #6 opened 2 years ago by Leymore
  1