LightOnOCR-1B-1025 / .eval_results /olmocrbench.yaml
Bapt120's picture
Update .eval_results/olmocrbench.yaml
a930736 verified
- 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