Skip to content

workarena_l3 benchmark not found #320

Description

@lakshya-skyfall

Specifying the benchmark as "workarena_l3" raises an error. Is "workarena_l3_agent_curriculum_eval" the same as the set of L3 tasks from WorkArena? And if so, should this name be used instead of "workarena_l3"?

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