- dataset: id: Delores-Lin/MDPBench task_id: overall value: 63.9 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: digital value: 80.2 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: photographed value: 58.5 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: latin value: 73.7 date: "2026-04-28" 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: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: en value: 79.1 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: es value: 65.0 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: fr value: 62.1 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: id value: 72.9 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: it value: 82.9 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: nl value: 70.2 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: pt value: 83.8 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: vi value: 74.9 date: "2026-04-28" 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: 52.8 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: ar value: 64.2 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: hi value: 59.0 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: jp value: 50.5 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: ko value: 41.6 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: ru value: 54.3 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: th value: 51.4 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin - dataset: id: Delores-Lin/MDPBench task_id: zh value: 46.6 date: "2026-04-28" 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: 54.7 date: "2026-04-28" source: url: https://huggingface.co/datasets/Delores-Lin/MDPBench name: MDPBench leaderboard user: Delores-Lin