Reasoning

OCRBench v2

OCRBench v2: a large-scale bilingual (English + Chinese) text-centric benchmark for LMMs spanning eight capabilities (text recognition, referring, spotting, relation extraction, element parsing, mathematical calculation, visual text understanding, knowledge reasoning) with task-tailored metrics. Per-example predictions are ingested for InternVL2.5-26B (the one model with a released per-instance prediction file); response is a transparent per-example correctness flag and the raw model output is kept in the trace.