lmms_eval/tasks/mmbench/mmbench_cn_dev.yaml

task: "mmbench_cn_dev"
test_split: "dev"
metric_list:
  - metric: gpt_eval_score
    aggregation: !function cn_utils.mmbench_aggregate_dev_results_eval
    higher_is_better: true
  - metric: submission
    higher_is_better: true
    aggregation: !function cn_utils.mmbench_aggregate_dev_results
include: _default_template_mmbench_cn_yaml