LlamaIndex Launches ParseBench-2 Benchmark and New OCRia-1.5 Parsing Models

LlamaIndex released ParseBench-2, an open-source benchmark quantifying AI accuracy in extracting data from complex documents. The release also includes the OCRia-1.5 parsing models. LlamaParse achieved an overall score of 90.1 on the new benchmark, while the Claude Opus 5.5 model scored 92.7 in text parsing.