{"id":"minicpm-ocr-1-0","slug":"minicpm-ocr-1-0","name":"MiniCPM-OCR 1.0","orgId":"openbmb","family":"minicpm-ocr-1-0","releaseDate":null,"availability":"announced","openWeights":true,"license":null,"paramsTotal":null,"paramsSource":null,"contextWindow":null,"knowledgeCutoff":null,"modelCardUrl":"https://x.com/OpenBMB/status/2115124474882469955","hfRepo":null,"modalities":["image","text"],"aliases":["MiniCPM-OCR 1.0","minicpm-ocr-1.0","minicpm ocr 1.0","openbmb/minicpm-ocr-1.0","minicpm-ocr"],"aliasNote":null,"origin":"tracked","tracked":{"trackedSince":"2026-10-27","announced":"2026-10-27","blurb":"OpenBMB's document-parsing model, the first OCR-specific model in the MiniCPM-V/o family. It reads text, tables, formulas, charts and seals in Chinese and English documents and PDFs, including scans, photos and curved or skewed pages, and extracts key information. Open weights under Apache 2.0.","api":"none","openWeights":"yes","params":{"text":"1.3B","source":"Hugging Face model card (safetensors: 1,300,434,160)"},"facts":[{"label":"Base","value":"Trained for OCR on top of MiniCPM-V 4.6 (SigLIP vision encoder + Qwen3.5 language model)"},{"label":"Languages","value":"Chinese and English"},{"label":"Pipeline","value":"PP-DocLayoutV3 layout model + MiniCPM-OCR 1.0 + minicpmvocr SDK; outputs Markdown or JSON"},{"label":"Weights","value":"Hugging Face openbmb/MiniCPM-OCR-1.0, plus GGUF, AWQ, GPTQ and DSpark (speculative decoding) builds"},{"label":"Runtimes","value":"vLLM, SGLang, llama.cpp and Ollama"},{"label":"License","value":"Apache 2.0"},{"label":"API","value":"Online demo on ModelBest's platform; the lab links a document-parse API, but its GitHub API guide says the official hosted endpoint is still to be added","unsure":true}],"claims":["Lab claim: 93.68 on Real5-OmniDocBench and 54.7 on OCRBench v2, with the highest equal-weight average across OmniDocBench v1.6, Real5-OmniDocBench, Wild-OmniDocBench and olmOCR-Bench among the open OCR models OpenBMB compared.","Lab claim: 1.2 pages/s on an RTX 5090; with DSpark about 1.49x the throughput of PaddleOCR-VL-1.6 and 3.62x MinerU2.5 Pro."],"sources":[{"kind":"lab","title":"OpenBMB announcement on X","url":"https://x.com/OpenBMB/status/2115124474882469955","date":"2026-10-27"},{"kind":"repo","title":"OpenBMB/MiniCPM-OCR on GitHub","url":"https://github.com/OpenBMB/MiniCPM-OCR","date":"2026-10-27"},{"kind":"repo","title":"openbmb/MiniCPM-OCR-1.0 on Hugging Face","url":"https://huggingface.co/openbmb/MiniCPM-OCR-1.0"}],"firstBenchmark":null},"organization":{"id":"openbmb","name":"OpenBMB","slug":"openbmb","country":null,"url":"https://github.com/OpenBMB","color":"#11110F","mark":"O"},"price":null,"answer":{"word":"Pending benchmarks.","scope":"Announced Oct 27, 2026; no independent results yet.","lead":"As of Nov 3, 2026, MiniCPM-OCR 1.0 is pending benchmarks on isitsota: announced Oct 27, 2026, with no independent results on the boards we track yet.","confidence":"low"},"status":"PENDING_BENCHMARKS","verdicts":[]}