{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/ocrbench-v2-an-improved-benchmark-for","title":"OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning","arxiv_id":"2501.00321","date":"2024-12-31","proceeding":null,"authors":["Ling Fu","Biao Yang","Zhebin Kuang","Jiajun Song","Yuzhe Li","Linghao Zhu","Qidi Luo","Xinyu Wang","Hao Lu","Mingxin Huang","Zhang Li","Guozhi Tang","Bin Shan","Chunhui Lin","Qi Liu","Binghong Wu","Hao Feng","Hao liu","Can Huang","Jingqun Tang","Wei Chen","Lianwen Jin","Yuliang Liu","Xiang Bai"],"abstract":"Scoring the Optical Character Recognition (OCR) capabilities of Large Multimodal Models (LMMs) has witnessed growing interest recently. Existing benchmarks have highlighted the impressive performance of LMMs in text recognition; however, their abilities on 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 including street scene, receipt, formula, diagram, and so on), and thorough evaluation metrics, with a total of 10,000 human-verified question-answering pairs and a high proportion of difficult samples. After carefully benchmarking state-of-the-art LMMs on OCRBench v2, we find that 20 out of 22 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 benchmark and evaluation scripts are available at https://github.com/Yuliang-liu/MultimodalOCR.","url_abs":"https://arxiv.org/abs/2501.00321v1","url_pdf":"https://arxiv.org/pdf/2501.00321v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"ocrbench-v2-an-improved-benchmark-for","repo_url":"https://github.com/yuliang-liu/multimodalocr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"logical-reasoning","task_name":"Logical Reasoning"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2501.00321","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.00321"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yuliang-liu/multimodalocr","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":6},"by_repo_kind":{"official":{"samples":10,"ran":4,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"430917573735bb95","entry":"get_full_labels_results","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"MDPBench/metrics/show_result.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/MDPBench/metrics/show_result.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"430917573735bb95"}},{"code_sha256_prefix":"43053af6494bf204","entry":"parallel_process","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"MDPBench/metrics/parallel.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/MDPBench/metrics/parallel.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43053af6494bf204"}},{"code_sha256_prefix":"9de0183bdb6b45d3","entry":"sort_nested_dict","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"MDPBench/metrics/show_result.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/MDPBench/metrics/show_result.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9de0183bdb6b45d3"}},{"code_sha256_prefix":"cb9eaee96a223830","entry":"split_list","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"OCRBench/example.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/OCRBench/example.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cb9eaee96a223830"}},{"code_sha256_prefix":"3242c8f10997c354","entry":"calculate_average","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"OCRBench_v2/eval_scripts/get_score.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/OCRBench_v2/eval_scripts/get_score.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3242c8f10997c354"}},{"code_sha256_prefix":"fea16b5a5b9ae980","entry":"calculate_iou","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"OCRBench_v2/eval_scripts/IoUscore_metric.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/OCRBench_v2/eval_scripts/IoUscore_metric.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fea16b5a5b9ae980"}},{"code_sha256_prefix":"731510333d199449","entry":"extract_coordinates","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"OCRBench_v2/eval_scripts/IoUscore_metric.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/OCRBench_v2/eval_scripts/IoUscore_metric.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"731510333d199449"}},{"code_sha256_prefix":"3e418b81ad6bb2c4","entry":"get_groups","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"MDPBench/metrics/cal_metric.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/MDPBench/metrics/cal_metric.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e418b81ad6bb2c4"}},{"code_sha256_prefix":"98ce0f38dc778190","entry":"get_page_split","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"MDPBench/metrics/show_result.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/MDPBench/metrics/show_result.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"98ce0f38dc778190"}},{"code_sha256_prefix":"2936938c6970406f","entry":"process_args","repo":"yuliang-liu/multimodalocr","repo_kind":"official","path":"MDPBench/pdf_validation.py","file_url":"https://github.com/yuliang-liu/multimodalocr/blob/HEAD/MDPBench/pdf_validation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2936938c6970406f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}