- dataset:
    id: allenai/olmOCR-bench
    task_id: overall
  value: 76.1
  notes: "Excluding Headers & Footers category"
  source:
    url: https://huggingface.co/papers/2601.14251
    name: LightOnOCR technical report
    user: Bapt120
- dataset:
    id: allenai/olmOCR-bench
    task_id: arxiv_math
  value: 81.4
  source:
    url: https://huggingface.co/papers/2601.14251
    name: LightOnOCR technical report
    user: Bapt120
- dataset:
    id: allenai/olmOCR-bench
    task_id: old_scans_math
  value: 71.6 
  source:
    url: https://huggingface.co/papers/2601.14251
    name: LightOnOCR technical report
    user: Bapt120
- dataset:
    id: allenai/olmOCR-bench
    task_id: table_tests
  value: 76.4
  source:
    url: https://huggingface.co/papers/2601.14251
    name: LightOnOCR technical report
    user: Bapt120
- dataset:
    id: allenai/olmOCR-bench
    task_id: old_scans
  value: 35.2
  source:
    url: https://huggingface.co/papers/2601.14251
    name: LightOnOCR technical report
    user: Bapt120
- dataset:
    id: allenai/olmOCR-bench
    task_id: multi_column
  value: 80.0
  source:
    url: https://huggingface.co/papers/2601.14251
    name: LightOnOCR technical report
    user: Bapt120
- dataset:
    id: allenai/olmOCR-bench
    task_id: long_tiny_text
  value: 88.7
  source:
    url: https://huggingface.co/papers/2601.14251
    name: LightOnOCR technical report
    user: Bapt120
- dataset:
    id: allenai/olmOCR-bench
    task_id: headers_footers
  value: 35.5
  notes: "Instead of removing headers and footers, our model is trained for full-page transcription and explicitly rewards their presence (via flipped RLVR tests), which lowers this score under the original benchmark scoring."
  source:
    url: https://huggingface.co/papers/2601.14251
    name: LightOnOCR technical report
    user: Bapt120
- dataset:
    id: allenai/olmOCR-bench
    task_id: baseline
  value: 99.6
  source:
    url: https://huggingface.co/papers/2601.14251
    name: LightOnOCR technical report
    user: Bapt120