hkust-nlp/ceval Issues
gpt-4-1106-preview 有人测试过 test 的分数吗?
Updated 3HOW TO EVALUATE STEM???
Closed 1Leaderboard Update
Closed什么时候更新榜单呢?
Closed 1Leaderboard Update
ClosedLeaderboard Update
Closed 1public display
Closed 1模型是否真正掌握了相关知识而不是在猜答案?
Closed 3请问chatglm3-6b-base发布在哪里?
Closed 1请问下这个结论是根据哪些观察得来的?
Closed 1prompt行尾含有空格会发生什么?为什么不能有空格
Closed 1自然语言处理的相关任务属于知识型还是推理型任务呢?
Closed 1llama和其他模型评测时不同点
Closed 1关于确认CEval可以被hack之后的计划
Updated 3##
Closed官方示例加载数据集报错
Updated 8Atom-13B不是公开访问的模型
Closed 2测试集中的部分错误。
Closed 4只能单选吗?可以多选吗?
Closed 1public display
Closed 2申请公开
Closed 4C-Eval 提交规则限制
Closed 3请问模型公开结果需要做哪些动作呀?
Closed 1官网无法登录,无法提交答案
Closedprompt大于max_len时的处理方式?
Closed 1根据code/Readme.md中给出的示例尝试遇到问题
Closed 2art_studies_test.csv 中有题目错误
Closed 2Problematic question in test set
Closed 1提交结果问题
Closed 7结果提交的疑问
Closed 2题目错误
Closed 1chatgpt數據更新
Updated请问hf格式的llama模型有公开的测试代码吗
Updated 4chatglm-6b验证集复现出来和论文有一点小差异。
Closed 4能支持下最新出的baichuan-7B模型吗
Closed 1可以支持下Ziya-13B-v1.1嘛
Closed