We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing. ✅ It contains comprehensive evals against most other ma…

We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing. ✅ It contains comprehensive evals against most other major open-weight OCR models (e.g. Infinity-Parser, LightOnOCR 3, Chandra 2, dots.mocr) on multiple OCR benchmarks: ParseBench, olmOCR-bench, PulseBench-Tab, fr-bench-pdf2md. ✅ It contains detailed visibility into our data and training pipeline, to give a glimpse into how we’re able to curate the right document datasets to push the evaluation metrics within dimensions that matter for doc parsing. ✅ It is blazing fast ⚡️ decoding 2x-4x+ faster than the latest open-weight models. ✅ If you’re building your own vision models, there are 24 pages worth of appendix details (!!) that showcase all of our experimental findings from training to evals! Check it out: https://www.llamaindex.ai/ocria/ocria-1-technical-report.pdf Other links are in our blog! https://www.llamaindex.ai/blog/parse-ocria-1 Media Today we’re releasing OCRia-1, a frontier VLM for document parsing that sets a new SOTA in accuracy, cost, and latency. It not only sets a new high score on ParseBench (87.4), but also leads in three 3rd-party benchmarks: olmOCR-bench* (83.5 overall, 92.9 on tables!), PulseBench-…

Related

• We built one of the most comprehensive benchmarks for document extraction, and evaluated it across a lot of different systems: ✅ one-shot fr…
• Messy tables and scanned PDFs are where most parsing breaks. OCRia-1 doesn't. Huge work from our research team, and it's already powering al…
• super proud of our research team on this work. we beat models that are much larger and trained with order-of-magnitude more data. in the end…

Source: Jerry Liu (X) | 2026-10-25