Agents
For any VLM based OCR models `. . . . ` and other repeating pattern are super hard to handle. That why we spent so much time building Llamap…
For any VLM based OCR models `. . . . ` and other repeating pattern are super hard to handle. That why we spent so much time building Llamaparse! OCR is not solved! I asked an OCR model claiming SOTA
For any VLM based OCR models . . . . and other repeating pattern are super hard to handle. That why we spent so much time building Llamaparse! OCR is not solved! I asked an OCR model claiming SOTA on popular benchmarks to read one line from an 1881 contents page. It wrote 16,421 characters. Mostly dots.
Related
- Yesterday we launched OCRia-1, our new state-of-the-art document parsing model powering LlamaParse. Today, it’s on OpenDocRouter! Run it alo…
- We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing. ✅ It contains comprehensive evals against most other ma…
- If you have more complex documents that require more powerful vision-based processing, come check out LlamaParse: https://cloud.llamaindex.a…
- The difference with using VLMs for OCR vs. other tasks is that the ratio of output/input tokens is quite high - meaning the model can spend …
Source: Jerry Liu (X) | 2026-10-26