Skip to content
TheChatArchiveThe Chat Archive
Claudeclaude-instant-1· AnthropicHugging Face Arena Human Preference 55K

Given a user query, create a plan to solve it with the utmost parallelizability. Each…

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with gpt-3.5-turbo-1106’s answer.
  1. User

    Given a user query, create a plan to solve it with the utmost parallelizability. Each plan should comprise an action from the following 2 types:

    1. data_analysis(entity: str) -> str:
    • 连接着一个关于负荷数据的数据库。
    • 包含一个python解释器,可以执行代码计算数学问题。
    • 如果查询执行成功,会返回执行结果。
    • entity: 一个完整的问题,比如XX公司XXXX年X月最大(小)负荷,XX公司XXXX年第X季度平均负荷等。
    1. join():
    • Collects and combines results from prior actions.
    • A LLM agent is called upon invoking join to either finalize the user query or wait until the plans are executed.
    • join should always be the last action in the plan, and will be called in two scenarios: (a) if the answer can be determined by gathering the outputs from tasks to generate the final response. (b) if the answer cannot be determined in the planning phase before you execute the plans.

    Guidelines:

    • Each action described above contains input/output types and description.
      • You must strictly adhere to the input and output types for each action.
      • The action descriptions contain the guidelines. You MUST strictly follow those guidelines when you use the actions.
    • Each action in the plan should strictly be one of the above types. Follow the Python conventions for each action.
    • Each action MUST have a unique ID, which is strictly increasing.
    • Inputs for actions can either be constants or outputs from preceding actions. In the latter case, use the format $id to denote the ID of the previous action whose output will be the input.
    • Always call join as the last action in the plan. Say '<END_OF_PLAN>' after you call join
    • Ensure the plan maximizes parallelizability.
    • Only use the provided action types. If a query cannot be addressed using these, invoke the join action for the next steps.
    • Never explain the plan with comments (e.g. #).
    • Never introduce new actions other than the ones provided.

    下面是一些名词解释:

    几创新高:即几次创下新高,首先需要查询前高是多少,再计算当前统计值几次高于前高。 几创新低:即几次创下新低,首先需要查询前低是多少,再计算当前统计值几次低于前低。 同比:与上一年同期比较。 环比:与上一统计周期比较。

    下面是一些例子:

    问题:XX公司XXXX年第X季度负荷相较XXXY年几次创下新高?

    1. data_analysis("请问XX公司XXXY年第X季度最大负荷是多少?")
    2. data_analysis("请问XX公司XXXX年第X季度最大负荷是多少?")
    3. data_analysis("请计算XX公司XXXX年第X季度负荷高于 $1 的次数") 想法:我现在可以回答这个问题了。
    4. join()<END_OF_PLAN>

    问题:XX公司XXXX年XX负荷是?同比有何变化?

    1. data_analysis("请问XX公司XXXX-1年XX负荷是多少?")
    2. data_analysis("请问XX公司XXXX年XX负荷是多少?")
    3. data_analysis("(2−2 - 1) / $1") 想法:我现在可以回答这个问题了。
    4. join()<END_OF_PLAN>

    问题:XX公司XXXX年XX月XX负荷是?环比有何变化?

    1. data_analysis("请问XX公司XXXX年XX-1月XX负荷是多少?")
    2. data_analysis("请问XX公司XXXX年XX月XX负荷是多少?")
    3. data_analysis("(2−2 - 1) / $1") 想法:我现在可以回答这个问题了。
    4. join()<END_OF_PLAN>

    问题: 请问直供区2023年3季度负荷相较去年同期几创新高?

  2. Claude Assistant

    Here is the plan to solve the user query with maximum parallelizability:

    1. data_analysis("请问直供区2022年3季度最大负荷是多少?")
    2. data_analysis("请问直供区2023年3季度最大负荷是多少?")
    3. data_analysis("请计算直供区2023年3季度负荷高于$1的次数")
    4. join()<END_OF_PLAN>

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.