.eval_results/olm_ocr_bench.yaml

- dataset:
    id: allenai/olmOCR-bench
    task_id: overall
  value: 79.8
  source:
    url: https://huggingface.co/papers/2603.13398
    name: Qianfan-OCR technical report
    user: nielsr
- dataset:
    id: allenai/olmOCR-bench
    task_id: arxiv_math
  value: 80.1
  source:
    url: https://huggingface.co/papers/2603.13398
    name: Qianfan-OCR technical report
    user: nielsr
- dataset:
    id: allenai/olmOCR-bench
    task_id: old_scans_math
  value:  73.1
  source:
    url: https://huggingface.co/papers/2603.13398
    name: Qianfan-OCR technical report
    user: nielsr
- dataset:
    id: allenai/olmOCR-bench
    task_id: table_tests
  value: 81.6
  source:
    url: https://huggingface.co/papers/2603.13398
    name: Qianfan-OCR technical report
    user: nielsr
- dataset:
    id: allenai/olmOCR-bench
    task_id: old_scans
  value:  42.0
  source:
    url: https://huggingface.co/papers/2603.13398
    name: Qianfan-OCR technical report
    user: nielsr
- dataset:
    id: allenai/olmOCR-bench
    task_id: multi_column
  value: 80.4
  source:
    url: https://huggingface.co/papers/2603.13398
    name: Qianfan-OCR technical report
    user: nielsr
- dataset:
    id: allenai/olmOCR-bench
    task_id: long_tiny_text
  value: 89.1
  source:
    url: https://huggingface.co/papers/2603.13398
    name: Qianfan-OCR technical report
    user: nielsr
- dataset:
    id: allenai/olmOCR-bench
    task_id: headers_footers
  value: 92.2
  source:
    url: https://huggingface.co/papers/2603.13398
    name: Qianfan-OCR technical report
    user: nielsr
- dataset:
    id: allenai/olmOCR-bench
    task_id: baseline
  value:  99.6
  source:
    url: https://huggingface.co/papers/2603.13398
    name: Qianfan-OCR technical report
    user: nielsr