eval.yaml

# 

name: Humanity's Last Exam
description: >
  Humanity's Last Exam (HLE) is a multi-modal benchmark at the frontier of human
  knowledge, designed to be the final closed-ended academic benchmark of its
  kind with broad subject coverage. Humanity's Last Exam consists of 2,500
  questions across dozens of subjects, including mathematics, humanities, and
  the natural sciences. HLE is developed globally by subject-matter experts and
  consists of multiple-choice and short-answer questions suitable for automated
  grading.

tasks:
  - id: hle
    config: default
    split: test

    field_spec:
      input: question
      input_image: image
      target: answer

    solvers:
      - name: system_message
        args:
          template: |
            Your response should be in the following format:

            Explanation: {your explanation for your answer choice}
            Answer: {your chosen answer}
            Confidence: {your confidence score between 0% and 100% for your answer}
      - name: generate

    scorers:
      - name: model_graded_fact
        args:
          model: openai/o3-mini