.eval_results/olmocrbench.yaml

- dataset:
    id: allenai/olmOCR-bench
    task_id: overall
  value: 82.1
  source:
    url: https://huggingface.co/OrionLLM/GRM-OCR
    name: GRM-OCR Model Card
    user: DedeProGames
  notes: English-subset only

- dataset:
    id: allenai/olmOCR-bench
    task_id: arxiv_math
  value: 80.5
  source:
    url: https://huggingface.co/OrionLLM/GRM-OCR
    name: GRM-OCR Model Card
    user: DedeProGames
  notes: English-subset only

- dataset:
    id: allenai/olmOCR-bench
    task_id: old_scans_math
  value: 71.8
  source:
    url: https://huggingface.co/OrionLLM/GRM-OCR
    name: GRM-OCR Model Card
    user: DedeProGames
  notes: English-subset only

- dataset:
    id: allenai/olmOCR-bench
    task_id: table_tests
  value: 89.5
  source:
    url: https://huggingface.co/OrionLLM/GRM-OCR
    name: GRM-OCR Model Card
    user: DedeProGames
  notes: English-subset only

- dataset:
    id: allenai/olmOCR-bench
    task_id: old_scans
  value: 42.5
  source:
    url: https://huggingface.co/OrionLLM/GRM-OCR
    name: GRM-OCR Model Card
    user: DedeProGames
  notes: English-subset only

- dataset:
    id: allenai/olmOCR-bench
    task_id: headers_footers
  value: 95.8
  source:
    url: https://huggingface.co/OrionLLM/GRM-OCR
    name: GRM-OCR Model Card
    user: DedeProGames
  notes: English-subset only

- dataset:
    id: allenai/olmOCR-bench
    task_id: multi_column
  value: 88.7
  source:
    url: https://huggingface.co/OrionLLM/GRM-OCR
    name: GRM-OCR Model Card
    user: DedeProGames
  notes: English-subset only

- dataset:
    id: allenai/olmOCR-bench
    task_id: long_tiny_text
  value: 78.3
  source:
    url: https://huggingface.co/OrionLLM/GRM-OCR
    name: GRM-OCR Model Card
    user: DedeProGames
  notes: English-subset only

- dataset:
    id: allenai/olmOCR-bench
    task_id: baseline
  value: 99.8
  source:
    url: https://huggingface.co/OrionLLM/GRM-OCR
    name: GRM-OCR Model Card
    user: DedeProGames
  notes: English-subset only