[KongchangAI]
Model

OvisOCR2

A document OCR parsing model with 0.8B parameters that scores 96.47 on OmniDocBench v1.6.

Timeline (last 90 days)

Oct 27

In a test running all 21 models on a fixed set of 100 OmniDocBench pages on a single RTX PRO 6000, OXR end-to-end (including layout analysis, recognition, and reading order) processed 100 pages in 101 seconds, while the next fastest, OvisOCR2, took 135 seconds.

Unverified50%
Oct 12

On OmniDocBench v1.6, TeleOCR outperforms Youtu-Parsing-Omni on text edit distance and table TEDS; OvisOCR2 and PaddleOCR-VL surpass Youtu on formulas with fewer than 1B parameters.

Expired50%

All Facts (1)

Unverified

In a test running all 21 models on a fixed set of 100 OmniDocBench pages on a single RTX PRO 6000, OXR end-to-end (including layout analysis, recognition, and reading order) processed 100 pages in 101 seconds, while the next fastest, OvisOCR2, took 135 seconds.

50%

Source Articles

OXR: 1.3B Open-Source Document Parsing Model Tops Three Major BenchmarksOct 27Youtu-Parsing-Omni In-Depth Review: Is a 5B-Parameter PDF Parser Worth Deploying?Oct 12