- dataset:
    id: Delores-Lin/MDPBench
    task_id: overall
  value: 42.7
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: digital
  value: 59.7
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: photographed
  value: 37.0
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: latin
  value: 53.4
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: de
  value: 39.8
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: en
  value: 64.2
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: es
  value: 47.5
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: fr
  value: 42.7
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: id
  value: 53.8
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: it
  value: 60.6
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: nl
  value: 52.2
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: pt
  value: 63.2
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: vi
  value: 57.0
  date: '2026-07-03'
  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: 30.6
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: ar
  value: 8.2
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: hi
  value: 9.0
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: jp
  value: 45.6
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: ko
  value: 30.3
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: ru
  value: 26.1
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: th
  value: 10.8
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: zh
  value: 55.3
  date: '2026-07-03'
  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: 59.3
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin
- dataset:
    id: Delores-Lin/MDPBench
    task_id: private
  value: 45.3
  date: '2026-07-03'
  source:
    url: https://huggingface.co/datasets/Delores-Lin/MDPBench
    name: MDPBench leaderboard
    user: Delores-Lin