Bug Eval Issue 561 Open Compassopencompass Github

[Bug]: Onboard Feature Bug · Issue #67546 · openclaw/openclaw · GitHub
[Bug]: Onboard Feature Bug · Issue #67546 · openclaw/openclaw · GitHub
Bug · Issue #67217 · openclaw/openclaw · GitHub
Bug · Issue #67217 · openclaw/openclaw · GitHub
[Bug] checkpoint load bug · Issue #832 · open-compass/opencompass · GitHub
[Bug] checkpoint load bug · Issue #832 · open-compass/opencompass · GitHub
[Bug] eval结果为空 · Issue #561 · open-compass/opencompass · GitHub
[Bug] eval结果为空 · Issue #561 · open-compass/opencompass · GitHub
[Bug] cannot use GPU when conduct evaluation · Issue #1759 · open ...
[Bug] cannot use GPU when conduct evaluation · Issue #1759 · open ...
[Bug] Only Debug Mode can perform eval tasks correctly. · Issue #1859 ...
[Bug] Only Debug Mode can perform eval tasks correctly. · Issue #1859 ...
[Bug] 评测C-Eval数据集时,选择test目录下测试数据,但是最后得分非常低,接近于0分 · Issue #952 · open ...
[Bug] 评测C-Eval数据集时,选择test目录下测试数据,但是最后得分非常低,接近于0分 · Issue #952 · open ...
[Bug] Evaluation of BBH · Issue #257 · open-compass/opencompass · GitHub
[Bug] Evaluation of BBH · Issue #257 · open-compass/opencompass · GitHub
[Bug] CLUEWSC的测试结果全是 50% · Issue #1174 · open-compass/opencompass · GitHub
[Bug] CLUEWSC的测试结果全是 50% · Issue #1174 · open-compass/opencompass · GitHub
[Bug] 评估过程中的oom 问题 · Issue #1587 · open-compass/opencompass · GitHub
[Bug] 评估过程中的oom 问题 · Issue #1587 · open-compass/opencompass · GitHub
[Bug] humaneval dataset infer success, but eval failed · Issue #364 ...
[Bug] humaneval dataset infer success, but eval failed · Issue #364 ...
[Bug] c-eval数据集下载报错 · Issue #2035 · open-compass/opencompass · GitHub
[Bug] c-eval数据集下载报错 · Issue #2035 · open-compass/opencompass · GitHub
[Bug] 官网1.0评测数据集链接失效 · Issue #942 · open-compass/opencompass · GitHub
[Bug] 官网1.0评测数据集链接失效 · Issue #942 · open-compass/opencompass · GitHub
[Bug] 更新代码后推理报错 · Issue #702 · open-compass/opencompass · GitHub
[Bug] 更新代码后推理报错 · Issue #702 · open-compass/opencompass · GitHub
[Bug] 运行ceval无法结果可视化 · Issue #383 · open-compass/opencompass · GitHub
[Bug] 运行ceval无法结果可视化 · Issue #383 · open-compass/opencompass · GitHub
[Bug] 评测结果为空 · Issue #670 · open-compass/opencompass · GitHub
[Bug] 评测结果为空 · Issue #670 · open-compass/opencompass · GitHub
cmb_gen [bug] · Issue #1137 · open-compass/opencompass · GitHub
cmb_gen [bug] · Issue #1137 · open-compass/opencompass · GitHub
[Bug]: · Issue #58218 · openclaw/openclaw · GitHub
[Bug]: · Issue #58218 · openclaw/openclaw · GitHub
[Bug] 讯飞的api疑似有故障 · Issue #659 · open-compass/opencompass · GitHub
[Bug] 讯飞的api疑似有故障 · Issue #659 · open-compass/opencompass · GitHub
[Bug] mmlupro 正则提取错误 · Issue #1661 · open-compass/opencompass · GitHub
[Bug] mmlupro 正则提取错误 · Issue #1661 · open-compass/opencompass · GitHub
[Bug] 找不到LongContext的数据集 · Issue #1047 · open-compass/opencompass · GitHub
[Bug] 找不到LongContext的数据集 · Issue #1047 · open-compass/opencompass · GitHub
[Bug] 为什么按官方文档跑会报错? · Issue #799 · open-compass/opencompass · GitHub
[Bug] 为什么按官方文档跑会报错? · Issue #799 · open-compass/opencompass · GitHub
[Bug] 3.24版本模型多次传递空参数导致工具调用失败 · Issue #56156 · openclaw/openclaw · GitHub
[Bug] 3.24版本模型多次传递空参数导致工具调用失败 · Issue #56156 · openclaw/openclaw · GitHub
[Bug] 自定义模型评测配置 · Issue #1746 · open-compass/opencompass · GitHub
[Bug] 自定义模型评测配置 · Issue #1746 · open-compass/opencompass · GitHub
[Bug] 按文档使用gpt3.5 测试数据集报错 · Issue #1270 · open-compass/opencompass · GitHub
[Bug] 按文档使用gpt3.5 测试数据集报错 · Issue #1270 · open-compass/opencompass · GitHub
[Bug]: Critical Bug Report: Browser Tool · Issue #24985 · openclaw ...
[Bug]: Critical Bug Report: Browser Tool · Issue #24985 · openclaw ...
[Bug] 增加数据集时失败 · Issue #1245 · open-compass/opencompass · GitHub
[Bug] 增加数据集时失败 · Issue #1245 · open-compass/opencompass · GitHub
[Bug]: · Issue #62380 · openclaw/openclaw · GitHub
[Bug]: · Issue #62380 · openclaw/openclaw · GitHub
[Bug] 不支持windows系统运行吗 · Issue #1300 · open-compass/opencompass · GitHub
[Bug] 不支持windows系统运行吗 · Issue #1300 · open-compass/opencompass · GitHub
[Bug]: Github Copilot add model failed on openclaw configure · Issue ...
[Bug]: Github Copilot add model failed on openclaw configure · Issue ...
[Bug]: · Issue #60516 · openclaw/openclaw · GitHub
[Bug]: · Issue #60516 · openclaw/openclaw · GitHub
[Bug] 评测速度很慢 · Issue #974 · open-compass/opencompass · GitHub
[Bug] 评测速度很慢 · Issue #974 · open-compass/opencompass · GitHub
[Bug] Medbench dataset · Issue #843 · open-compass/opencompass · GitHub
[Bug] Medbench dataset · Issue #843 · open-compass/opencompass · GitHub
运行评测结果为空[Bug] · Issue #1304 · open-compass/opencompass · GitHub
运行评测结果为空[Bug] · Issue #1304 · open-compass/opencompass · GitHub
[Bug]: a · Issue #60688 · openclaw/openclaw · GitHub
[Bug]: a · Issue #60688 · openclaw/openclaw · GitHub
[Bug] 评测lawbench数据集时偶现异常 · Issue #1185 · open-compass/opencompass · GitHub
[Bug] 评测lawbench数据集时偶现异常 · Issue #1185 · open-compass/opencompass · GitHub

Loading image details...

Source
Dimensions