.eval_results/mdpbench.yaml

- dataset:
    id: Delores-Lin/MDPBench
    task_id: overall
  value: 56.3
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: digital
  value: 72.4
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: photographed
  value: 51.1
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: latin
  value: 69.3
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: de
  value: 72.4
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: en
  value: 75.0
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: es
  value: 60.9
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: fr
  value: 61.8
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: id
  value: 69.6
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: it
  value: 74.7
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: nl
  value: 71.6
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: pt
  value: 70.3
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: vi
  value: 67.8
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: non_latin
  value: 41.6
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: ar
  value: 37.9
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: hi
  value: 61.3
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: jp
  value: 39.6
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: ko
  value: 29.6
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: ru
  value: 54.0
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: th
  value: 24.8
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: zh
  value: 39.7
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin

- dataset:
    id: Delores-Lin/MDPBench
    task_id: zh_t
  value: 45.6
  date: "2026-06-08"
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin