Model Releases
The llamas learned to read. OCRia-1 is live in LlamaParse: our own parsing model, 12+ points ahead of the next-best on ParseBench, way bette…
The llamas learned to read. OCRia-1 is live in LlamaParse: our own parsing model, 12+ points ahead of the next-best on ParseBench, way better on tables and charts. Same price, no drama llama. Got a do
The llamas learned to read. OCRia-1 is live in LlamaParse: our own parsing model, 12+ points ahead of the next-best on ParseBench, way better on tables and charts. Same price, no drama llama. Got a doc that breaks every parser? Send it my way. 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
- cria == baby llama 🦙
- 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 n…
Source: Jerry Liu (X) | 2026-10-22