group: mmlu_generative group_alias: mmlu (generative) task: - group: stem task: - mmlu_stem_generative aggregate_metric_list: - metric: exact_match weight_by_size: true - group: other task: - mmlu_other_generative aggregate_metric_list: - metric: exact_match weight_by_size: true - group: social sciences task: - mmlu_social_sciences_generative aggregate_metric_list: - metric: exact_match weight_by_size: true - group: humanities task: - mmlu_humanities_generative aggregate_metric_list: - metric: exact_match weight_by_size: true aggregate_metric_list: - aggregation: mean metric: exact_match weight_by_size: true metadata: version: 3