# Optical Character Recognition on olmOCR multiple category 1.5 Source: [Optical Character Recognition on olmOCR multiple category 1.5]() Collection index: [llms.txt]() Data updated: 2026-03-31T08:40:30.849Z Evaluation of Optical Character Recognition performance on the olmOCR multiple category 1.5 dataset, reporting specific accuracies across various categories like math, tables, and multi-column text. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Optical Character Recognition | | Dataset (including any stated split) | olmOCR multiple category 1.5 | | Metric | Average Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 9 of 9 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Average Accuracy](): Higher is better; unit: PERCENT. - [Math Accuracy (ArXiv)](): Higher is better; unit: PERCENT. - [Base Accuracy](): Higher is better; unit: PERCENT. - [Header/Footer Accuracy](): Higher is better; unit: PERCENT. - [TinyTxt Accuracy](): Higher is better; unit: PERCENT. - [Multi-Column Accuracy](): Higher is better; unit: PERCENT. - [Old Scan Accuracy](): Higher is better; unit: PERCENT. - [Old Math Accuracy](): Higher is better; unit: PERCENT. - [Tables Accuracy](): Higher is better; unit: PERCENT. ## Recorded results | Method | Average Accuracy | Result date | Report paper | | --- | --- | --- | --- | | Chandra | 82 | Not recorded | 69cb54fe0636e5bf4afc9e7c | | Mistral OCR 3 | 81.7 | Not recorded | 69cb54fe0636e5bf4afc9e7c | | FalconOCR | 80.3 | Not recorded | 69cb54fe0636e5bf4afc9e7c | | Gemini 3 Pro | 80.2 | Not recorded | 69cb54fe0636e5bf4afc9e7c | | PaddleOCR VL 1.5 | 79.3 | Not recorded | 69cb54fe0636e5bf4afc9e7c | | PaddleOCR VL | 79.2 | Not recorded | 69cb54fe0636e5bf4afc9e7c | | DeepSeek OCR v2 | 78.8 | Not recorded | 69cb54fe0636e5bf4afc9e7c | | Gemini 3 Flash | 77.5 | Not recorded | 69cb54fe0636e5bf4afc9e7c | | GPT 5.2 | 69.8 | Not recorded | 69cb54fe0636e5bf4afc9e7c | ### Chandra Average Accuracy: 82. Result ID: 69cb886b47f34ce924b3dcdf. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Mistral OCR 3 Average Accuracy: 81.7. Result ID: 69cb886b47f34ce924b3dcde. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### FalconOCR Average Accuracy: 80.3. Result ID: 69cb886b47f34ce924b3dce6. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini 3 Pro Average Accuracy: 80.2. Result ID: 69cb886b47f34ce924b3dce0. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PaddleOCR VL 1.5 Average Accuracy: 79.3. Result ID: 69cb886b47f34ce924b3dce1. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### PaddleOCR VL Average Accuracy: 79.2. Result ID: 69cb886b47f34ce924b3dce2. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### DeepSeek OCR v2 Average Accuracy: 78.8. Result ID: 69cb886b47f34ce924b3dce3. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### Gemini 3 Flash Average Accuracy: 77.5. Result ID: 69cb886b47f34ce924b3dce4. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. ### GPT 5.2 Average Accuracy: 69.8. Result ID: 69cb886b47f34ce924b3dce5. [Reporting paper]() Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.