group: agieval_nous task: - agieval_aqua_rat - agieval_logiqa_en - agieval_lsat_ar - agieval_lsat_lr - agieval_lsat_rc - agieval_sat_en_without_passage - agieval_sat_en - agieval_sat_math aggregate_metric_list: - metric: acc_norm aggregation: mean weight_by_size: true metadata: version: 0.0