Skip to content

The Details of Evaluation on Math Benchmark #6

Description

@ba1jun

Hi Multiverse Team,

Thank you for your remarkable work! Could you share more details on how you conducted the evaluation of Multiverse-32B on AIME24, AIME25, and MATH500—for example, the prompts used, generation configurations, and the maximum number of new tokens?

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions