{"work":{"id":"58bef901-2b24-42dd-9edc-28c0b2148490","openalex_id":"https://openalex.org/W4406031111","doi":"10.48550/arxiv.2501.00321","arxiv_id":"2501.00321","raw_key":null,"title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","authors":null,"authors_text":"Ling Fu, Zhebin Kuang, Jiajun Song, Mingxin Huang, Biao Yang, Yuzhe Li","year":2024,"venue":"cs.CV","abstract":"Scoring the Optical Character Recognition (OCR) capabilities of Large Multimodal Models (LMMs) has witnessed growing interest. Existing benchmarks have highlighted the impressive performance of LMMs in text recognition; however, their abilities in certain challenging tasks, such as text localization, handwritten content extraction, and logical reasoning, remain underexplored. To bridge this gap, we introduce OCRBench v2, a large-scale bilingual text-centric benchmark with currently the most comprehensive set of tasks (4x more tasks than the previous multi-scene benchmark OCRBench), the widest coverage of scenarios (31 diverse scenarios), and thorough evaluation metrics, with 10,000 human-verified question-answering pairs and a high proportion of difficult samples. Moreover, we construct a private test set with 1,500 manually annotated images. The consistent evaluation trends observed across both public and private test sets validate the OCRBench v2's reliability. After carefully benchmarking state-of-the-art LMMs, we find that most LMMs score below 50 (100 in total) and suffer from five-type limitations, including less frequently encountered text recognition, fine-grained perception, layout perception, complex element parsing, and logical reasoning. The project website is at: https://99franklin.github.io/ocrbench_v2/","external_url":"https://arxiv.org/abs/2501.00321","cited_by_count":2,"metadata_source":"pith","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":"2501.00321","created_at":"2026-05-09T01:54:36.077606+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","render_title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning"},"hub":{"state":{"work_id":"58bef901-2b24-42dd-9edc-28c0b2148490","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":31,"external_cited_by_count":2,"distinct_field_count":4,"first_pith_cited_at":"2025-09-26T10:45:48+00:00","last_pith_cited_at":"2026-07-02T02:04:07+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T07:39:37.329422+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3},{"context_role":"baseline","n":3},{"context_role":"dataset","n":1}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"baseline","n":3},{"context_polarity":"use_dataset","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}