Update README.md

README.md

@@ -15,13 +15,14 @@ tags:
 
 # Chandra OCR 2
 
-Chandra 2 is an OCR model from [Datalab](https://www.datalab.to) that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information.
+Chandra 2 is a state of the art OCR model from [Datalab](https://www.datalab.to) that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information.
 
 Try Chandra in the [free playground](https://www.datalab.to/playground), or use the [hosted API](https://www.datalab.to/) for higher accuracy and speed.
 
 ## What's New in Chandra 2
 
-- Significant improvements to math, tables, and multilingual OCR
+- 85.9% olmocr bench score (sota), 77.8% multilingual bench score (12% improvement over Chandra 1)
+- Significant improvements to math, tables, complex layouts
 - Improved layout, especially on wider documents
 - Significantly better image captioning
 - 90+ language support with major accuracy gains