lm_eval/tasks/leaderboard/leaderboard.yaml

group: leaderboard
task:
  - leaderboard_mmlu_pro
  - leaderboard_bbh
  - leaderboard_gpqa
  - leaderboard_math_hard
  - leaderboard_ifeval
  - leaderboard_musr
aggregate_metric_list:
  - metric: acc
    aggregation: mean
    weight_by_size: true # defaults to `true`. Set this to `false` to do a "macro" average (taking each subtask's average accuracy, and summing those accuracies and dividing by 3)--by default we do a "micro" average (retain all subtasks' per-document accuracies, and take the mean over all documents' accuracies to get our aggregate mean).
  - metric: acc_norm
    aggregation: mean
    weight_by_size: true # defaults to `true`. Set this to `false` to do a "macro" average (taking each subtask's average accuracy, and summing those accuracies and dividing by 3)--by default we do a "micro" average (retain all subtasks' per-document accuracies, and take the mean over all documents' accuracies to get our aggregate mean).
  - metric: exact_match
    aggregation: mean
    weight_by_size: true # defaults to `true`. Set this to `false` to do a "macro" average (taking each subtask's average accuracy, and summing those accuracies and dividing by 3)--by default we do a "micro" average (retain all subtasks' per-document accuracies, and take the mean over all documents' accuracies to get our aggregate mean).
  - metric: inst_level_loose_acc
    aggregation: mean
    weight_by_size: true # defaults to `true`. Set this to `false` to do a "macro" average (taking each subtask's average accuracy, and summing those accuracies and dividing by 3)--by default we do a "micro" average (retain all subtasks' per-document accuracies, and take the mean over all documents' accuracies to get our aggregate mean).
  - metric: inst_level_strict_acc
    aggregation: mean
    weight_by_size: true # defaults to `true`. Set this to `false` to do a "macro" average (taking each subtask's average accuracy, and summing those accuracies and dividing by 3)--by default we do a "micro" average (retain all subtasks' per-document accuracies, and take the mean over all documents' accuracies to get our aggregate mean).
  - metric: prompt_level_loose_acc
    aggregation: mean
    weight_by_size: true # defaults to `true`. Set this to `false` to do a "macro" average (taking each subtask's average accuracy, and summing those accuracies and dividing by 3)--by default we do a "micro" average (retain all subtasks' per-document accuracies, and take the mean over all documents' accuracies to get our aggregate mean).
  - metric: prompt_level_strict_acc
    aggregation: mean
    weight_by_size: true # defaults to `true`. Set this to `false` to do a "macro" average (taking each subtask's average accuracy, and summing those accuracies and dividing by 3)--by default we do a "micro" average (retain all subtasks' per-document accuracies, and take the mean over all documents' accuracies to get our aggregate mean).
metadata:
  version: 1.0