Specialist modelOpen weights
TeleOCR
TeleAI
- Released
- August 17, 2026
- Data date
- October 3, 2026
- Model class
TeleOCR is a lightweight vision-language model for document parsing. It handles digital and camera-captured documents and targets tables, formulas, layout, and content. The checkpoint has approximately 1.2 billion parameters and is released for local execution.
The weights were first released as NaviDC-OCR on August 17, 2026. The project renamed the model to TeleOCR on September 10. It remains one Apache-2.0 checkpoint rather than two separate models.
Specifications and access
| Specification | Value and source |
|---|---|
| Current model ID | XingChen-AGI/TeleOCRSource |
| Former model ID | NaviDC-OCR, renamed to TeleOCR on September 10, 2026Source |
| Model class | Vision-language model for document parsingSource |
| Parameters | Approximately 1.2 billionSource |
| Documents | Digital and camera-captured documents with tables and formulasSource |
| License | Apache-2.0Source |
Page 1 of 2
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
Dr.DocBench overall (Show measurement, test conditions, and source)
- Source value
- 67.96
- Score
- 67.96
- Metric
- unknown
- Unit
- No unit provided
- Category
- document-ocr
- Direction
- Higher is better
- Source type
- official-leaderboard
- Evaluator
- Dr.DocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Document-parsing challenge; historical row label NaviDC-OCR, mapped by the model card to TeleOCR native weights.
- Context
- Source-defined overall metric. The canonical profile retains the older navidc-ocr ID while displaying TeleOCR.
Dr.DocBench text edit (Show measurement, test conditions, and source)
- Source value
- 0.1903
- Score
- 0.1903
- Metric
- edit-distance
- Unit
- edit-distance
- Category
- document-ocr
- Direction
- Lower is better
- Source type
- official-leaderboard
- Evaluator
- Dr.DocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Document-parsing challenge; historical NaviDC-OCR native-weight row.
Dr.DocBench formula CDM (Show measurement, test conditions, and source)
- Source value
- 0.02
- Score
- 0.02
- Metric
- unknown
- Unit
- No unit provided
- Category
- document-ocr
- Direction
- Higher is better
- Source type
- official-leaderboard
- Evaluator
- Dr.DocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Document-parsing challenge; historical NaviDC-OCR native-weight row.
- Context
- Source-defined metric scale; the row's positive direction is retained.
Dr.DocBench table TEDS (Show measurement, test conditions, and source)
- Source value
- 64.97
- Score
- 64.97
- Metric
- unknown
- Unit
- No unit provided
- Category
- document-ocr
- Direction
- Higher is better
- Source type
- official-leaderboard
- Evaluator
- Dr.DocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Document-parsing challenge; historical NaviDC-OCR native-weight row.
- Context
- Source-defined metric scale.
Dr.DocBench order edit (Show measurement, test conditions, and source)
- Source value
- 0.398
- Score
- 0.398
- Metric
- edit-distance
- Unit
- edit-distance
- Category
- document-ocr
- Direction
- Lower is better
- Source type
- official-leaderboard
- Evaluator
- Dr.DocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Document-parsing challenge; historical NaviDC-OCR native-weight row.
OmniDocBench v1.6 overall (Show measurement, test conditions, and source)
- Source value
- 96.87
- Score
- 96.87
- Metric
- unknown
- Unit
- No unit provided
- Category
- document-ocr
- Direction
- Higher is better
- Source type
- official-leaderboard
- Evaluator
- OmniDocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Specialized VLM table; TeleOCR 1.2B row.
- Context
- Source-defined overall metric.
OmniDocBench v1.6 text edit (Show measurement, test conditions, and source)
- Source value
- 0.027
- Score
- 0.027
- Metric
- edit-distance
- Unit
- edit-distance
- Category
- document-ocr
- Direction
- Lower is better
- Source type
- official-leaderboard
- Evaluator
- OmniDocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Specialized VLM table; TeleOCR 1.2B row.
OmniDocBench v1.6 formula CDM (Show measurement, test conditions, and source)
- Source value
- 96.36
- Score
- 96.36
- Metric
- unknown
- Unit
- No unit provided
- Category
- document-ocr
- Direction
- Higher is better
- Source type
- official-leaderboard
- Evaluator
- OmniDocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Specialized VLM table; TeleOCR 1.2B row.
- Context
- Source-defined metric scale.
OmniDocBench v1.6 table TEDS (Show measurement, test conditions, and source)
- Source value
- 97.05
- Score
- 97.05
- Metric
- unknown
- Unit
- No unit provided
- Category
- document-ocr
- Direction
- Higher is better
- Source type
- official-leaderboard
- Evaluator
- OmniDocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Specialized VLM table; TeleOCR 1.2B row.
- Context
- Source-defined metric scale.
OmniDocBench v1.6 table TEDSS (Show measurement, test conditions, and source)
- Source value
- 98.52
- Score
- 98.52
- Metric
- unknown
- Unit
- No unit provided
- Category
- document-ocr
- Direction
- Higher is better
- Source type
- official-leaderboard
- Evaluator
- OmniDocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Specialized VLM table; TeleOCR 1.2B row.
- Context
- Source-defined metric scale.
OmniDocBench v1.6 read-order edit (Show measurement, test conditions, and source)
- Source value
- 0.122
- Score
- 0.122
- Metric
- edit-distance
- Unit
- edit-distance
- Category
- document-ocr
- Direction
- Lower is better
- Source type
- official-leaderboard
- Evaluator
- OmniDocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Specialized VLM table; TeleOCR 1.2B row.
Wild OmniDocBench overall (Show measurement, test conditions, and source)
- Source value
- 88.53
- Score
- 88.53
- Metric
- unknown
- Unit
- No unit provided
- Category
- document-ocr
- Direction
- Higher is better
- Source type
- official-leaderboard
- Evaluator
- Wild OmniDocBench
- Status
- active
- Retrieved at
- 2026-10-03
- Methodology
- Official benchmark leaderboard. Wild document benchmark; TeleOCR 1.2B row.
- Context
- Source-defined overall metric.
Page 1 of 2
Sources and data date
Every statement links to its underlying documentation or leaderboard.
| Type | Evidence and data date |
|---|---|
| Research status | Research date October 4, 2026. 6 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication. |
| Not found in the inspected sources | remaining-ocr-subtasks Original wording PureDocBench overall, formula, and table metrics, plus Sci-ImageMiner RMS, TEDS, and weighted values, have no sufficiently clear direction in the inspected sources. They remain unassigned rather than being guessed. |
| Additional source | TeleOCR model card (retrieved October 3, 2026) · TeleOCR model card · Editorial description reviewed October 3, 2026 |
| Additional source | TeleOCR technical report (retrieved October 3, 2026) · TeleOCR technical report · Editorial description reviewed October 3, 2026 |
| Additional source | Dr.DocBench (retrieved October 3, 2026) |
| Additional source | OmniDocBench (retrieved October 3, 2026) |
| Additional source | Wild OmniDocBench (retrieved October 3, 2026) |
| Additional source | PureDocBench (retrieved October 3, 2026) |
| Additional source | Model metadata (retrieved October 3, 2026) |