{ "data": { "a": { "slug": "nanbeige-4-3-33b", "name": "Nanbeige4.3-33B", "vendor": "Nanbeige LLM Lab (BOSS Zhipin)", "vendorUrl": "https://huggingface.co/Nanbeige", "kind": "weights", "category": "open-weights", "summary": "Nanbeige4.3-33B is the Nanbeige LLM Lab's open-weight dense model for agentic coding and office work, 33B parameters on the Llama architecture with a 512K-token context, thinking that switches per request and tool calls in an XML format.", "url": "https://www.anchorterminal.com/tools/nanbeige-4-3-33b", "markdownUrl": "https://www.anchorterminal.com/tools/nanbeige-4-3-33b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/nanbeige-4-3-33b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/nanbeige-4-3-33b.json", "repo": "https://huggingface.co/Nanbeige/Nanbeige4.3-33B", "license": "Apache-2.0 (Hub metadata only; the repository has no LICENSE file)", "transports": [], "packages": [ { "registry": "huggingface", "name": "Nanbeige/Nanbeige4.3-33B" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The Hub reports gated false for Nanbeige/Nanbeige4.3-33B and Nanbeige/Nanbeige4.3-33B-Base (checked 2026-10-25).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0 as the card's metadata names it. Neither repository holds a LICENSE file. Running it costs the hardware, 66.26 GB of BF16 files and no quantised build from the publisher. No hosted API or inference provider serves it (checked 2026-10-25).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-25).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-25" }, "docsUrl": "https://huggingface.co/Nanbeige/Nanbeige4.3-33B", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "llama", "reasoning", "tool-calling", "coding", "agentic", "long-context", "safetensors", "self-hosted", "new" ], "lastRelease": "2026-10-24", "graded": true, "anchor": { "graded": true, "score": 61, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1217, "categoryRank": 48, "methodology": "0.6", "run": "2026-10-01", "scores": { "interface": 85, "reach": 55, "risk": 60, "upkeep": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-25" }, "negative": 0, "verdict": "A dense 33B Llama-architecture cousin for long agentic coding and office tasks, with per-request thinking, XML tool calls that stock vLLM and SGLang parse, and 512K of context. It needs about 96 GB at BF16, as Nanbeige ships no quantised build. Its agentic results so far are Nanbeige's own, with no safety results, training data notes or licence file.", "bestFor": "Agents with about 96 GB of GPU memory, or the 128 GB reference machine, that want an Apache-tagged 33B model for long coding and tool loops and can wait for independent results.", "strengths": [ "A plain LlamaForCausalLM with no repository code, so released vLLM, SGLang, Transformers and llama.cpp load it", "Apache 2.0 by its metadata, ungated, safetensors only", "524,288 tokens of context set in config.json with no rope scaling", "Thinking switches per request, and preserve_thinking keeps earlier reasoning for agent loops", "Tool calls in an XML format the qwen3_coder parser reads, several per turn", "A Nanbeige member answered four of the first ten discussions on release day" ], "weaknesses": [ "No independent benchmark result yet; every agentic number on the card is Nanbeige's own run", "BF16 only from Nanbeige, about 80 GB to load, and no Ollama or LM Studio build", "No LICENSE file in either repository; Apache 2.0 rests on the metadata tag", "No safety evaluation, agent-use guidance, training data description or knowledge cut-off", "No hosted API or inference provider serves it" ], "agentNotes": [ "Serve with `vllm serve Nanbeige/Nanbeige4.3-33B --enable-auto-tool-choice --reasoning-parser qwen3 --tool-call-parser qwen3_coder`, as the card says, or SGLang with the same two parsers", "Keep `tool_call_format` at its default `xml`, since qwen3_coder parses that format; the `json` option writes Hermes-style JSON calls, which need a different parser such as vLLM's hermes", "Pass `chat_template_kwargs` `{\"preserve_thinking\": true}` for multi-turn tool use and coding, and `{\"enable_thinking\": false}` to skip reasoning, as the card recommends", "Use temperature 1.0, top_p 0.95 and up to 65,536 new tokens for agent work, and temperature 0.6 for reasoning and chat, per the card", "Send your own system prompt, since without one the template injects a Chinese identity line, or a Chinese tool-expert prompt when tools are passed", "Send one system message at the start only, as the template raises an error for a later one", "In plain Transformers pass `use_cache=True` to generate, since config.json and generation_config.json set it false; trust_remote_code isn't needed" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 85, "reach": 55, "risk": 60, "upkeep": 56 }, "provenanceScore": 53, "checked": { "categories": { "interface": "2026-10-25", "reach": "2026-10-25", "risk": "2026-10-25", "upkeep": "2026-10-25" }, "last": "2026-10-25", "oldest": "2026-10-25", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# vLLM 0.32.0 or SGLang 0.5.22, as the card's commands (the card uses four GPUs with tensor parallelism)\nhf download Nanbeige/Nanbeige4.3-33B --local-dir Nanbeige4.3-33B\nvllm serve ./Nanbeige4.3-33B --served-model-name nanbeige --tensor-parallel-size 4 \\\n --enable-auto-tool-choice --reasoning-parser qwen3 --tool-call-parser qwen3_coder\n# or\npython -m sglang.launch_server --model-path ./Nanbeige4.3-33B --tp-size 4 \\\n --reasoning-parser qwen3 --tool-call-parser qwen3_coder", "http": "curl http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' \\\n -d '{\"model\": \"nanbeige\", \"messages\": [{\"role\": \"user\", \"content\": \"Which number is bigger, 9.11 or 9.8?\"}],\n \"temperature\": 0.6, \"top_p\": 0.95, \"chat_template_kwargs\": {\"enable_thinking\": true}}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/nanbeige-4-3-33b" }, "weights": { "trainedBy": "Nanbeige LLM Lab (BOSS Zhipin)", "builtOn": "Nanbeige/Nanbeige4.3-33B-Base (fine-tune, declared in the card's metadata; Apache 2.0 by its tag, no LICENSE file)", "params": "33B", "context": 524288, "goodFor": "A cousin for long agentic coding and office tasks on a machine with about 96 GB of memory, if Nanbeige's own results hold up, with a 512K context and per-request thinking.", "runtimes": [ "vLLM", "SGLang", "Transformers", "llama.cpp" ], "builds": [ { "name": "Nanbeige4.3-33B (BF16)", "url": "https://huggingface.co/Nanbeige/Nanbeige4.3-33B", "who": "publisher", "precision": "bf16", "sizeGB": 66.26, "memoryGB": 96, "format": "safetensors", "runsOn": [ "vLLM", "SGLang", "Transformers" ], "note": "Whole repository, 66.24 GB of weights in 14 shards. 66.26 GB × 1.2 = 79.5 GB. The only build from Nanbeige; no Ollama, LM Studio or ggml-org build exists, and llama.cpp needs a GGUF converted with its own script or taken from someone else" } ], "run": "vllm serve Nanbeige/Nanbeige4.3-33B --tensor-parallel-size 4 --enable-auto-tool-choice --reasoning-parser qwen3 --tool-call-parser qwen3_coder", "runBuild": "Nanbeige4.3-33B (BF16)", "checked": "2026-10-25", "minMemoryGB": 96 }, "family": { "lab": "Nanbeige LLM Lab (BOSS Zhipin)", "family": "Nanbeige4.3", "url": "https://www.anchorterminal.com/open-weights/#nanbeige", "others": [ { "name": "Nanbeige4.3-33B-Base", "url": "https://huggingface.co/Nanbeige/Nanbeige4.3-33B-Base", "params": "33B" } ], "olderCount": 7 }, "area": "models", "provenance": { "legalEntity": "BOSS Zhipin (Kanzhun Limited), unconfirmed", "domain": "zhipin.com", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/Nanbeige/Nanbeige4.3-33B/commits/main", "securityTxt": "none", "checked": "2026-10-25", "notes": [ "The card names the Nanbeige Team and nothing else. BOSS Zhipin is identified as the maker by the lab's Nanbeige4.2-3B report on arXiv (Nanbeige LLM Lab, Boss Zhipin), which links huggingface.co/Nanbeige, and by the chat template's default system prompt naming BOSS Zhipin as developer and trainer. The card's contact address is on kanzhun.com. Kanzhun Limited as BOSS Zhipin's operator wasn't confirmed first-hand, since ir.zhipin.com refused our reader. The domain's registration date wasn't checked.", "The Hugging Face organisation Nanbeige (Nanbeige LLM Lab) isn't verified by the Hub. The arXiv report's link to it is the publisher's own documentation pointing there.", "Nothing is hosted, so the licence stands in for terms of service and no privacy policy is scored.", "The changelog is the repository's commit history.", "www.zhipin.com/.well-known/security.txt answers 404 and kanzhun.com's redirects to the home page. BOSS Zhipin runs a security response centre at security.zhipin.com for reporting flaws in its products; nothing links it to the model." ], "score": 53 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/nanbeige-4-3-33b.json", "live": { "slug": "nanbeige-4-3-33b", "securityTxt": { "url": "https://zhipin.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-27T15:32:16.316619103Z" }, "pages": [ { "url": "https://huggingface.co/Nanbeige/Nanbeige4.3-33B/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-10-27T03:47:53.67708636Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "3a395186681d" } ], "updatedAt": "2026-10-27T15:32:16.316619103Z" } }, "answer": "Nanbeige4.3-33B scores 61 (C) on agent readiness against Baidu Unlimited-OCR-2's 53.5 (D), and leads in 3 of 4 scored categories.", "b": { "slug": "unlimited-ocr-2", "name": "Baidu Unlimited-OCR-2", "vendor": "Baidu", "vendorUrl": "https://github.com/baidu", "kind": "weights", "category": "open-weights", "summary": "Unlimited-OCR-2 is Baidu's open-weight document OCR model, about 3.3B parameters, that parses page images, from one page to documents of hundreds of pages in one request, into layout blocks with boxes and HTML tables, under MIT.", "url": "https://www.anchorterminal.com/tools/unlimited-ocr-2", "markdownUrl": "https://www.anchorterminal.com/tools/unlimited-ocr-2.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/unlimited-ocr-2.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/unlimited-ocr-2.json", "repo": "https://huggingface.co/baidu/Unlimited-OCR-2", "license": "MIT (Hub metadata; the Hugging Face repository has no LICENSE file, and the GitHub code repository's LICENSE is the MIT text, copyright 2026 Baidu)", "transports": [], "packages": [ { "registry": "huggingface", "name": "baidu/Unlimited-OCR-2" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository isn't gated (checked 2026-10-27).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under MIT by the repository's metadata and the LICENSE file in Baidu's GitHub code repository. Baidu sells no per-call access to these weights in this listing. Running them costs the hardware, 6.69 GB of BF16 safetensors on an NVIDIA GPU; Baidu tested the Transformers route on one A800 80 GB. No inference provider serves it on Hugging Face (checked 2026-10-27).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-27).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-27" }, "docsUrl": "https://huggingface.co/baidu/Unlimited-OCR-2", "capabilities": [ "docs.ocr", "docs.parse", "docs.tables", "model.open-weights" ], "tags": [ "open-weights", "model", "ocr", "document-parsing", "multi-page", "long-documents", "tables", "layout", "bounding-boxes", "vision", "mixture-of-experts", "safetensors", "self-hosted", "new" ], "lastRelease": "2026-10-26", "graded": true, "anchor": { "graded": true, "score": 53.5, "grade": "D", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1217, "categoryRank": 74, "methodology": "0.6", "run": "2026-10-01", "scores": { "interface": 75, "reach": 55, "risk": 45, "upkeep": 45 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-27" }, "negative": 0, "verdict": "A small MIT document-parsing cousin that reads up to hundreds of pages in one request and returns ordered layout blocks with boxes and HTML tables. It needs an NVIDIA GPU with about 12 GB, through Baidu's remote code or its own SGLang build. The risks are running the publisher's code and accuracy figures that are Baidu's own.", "bestFor": "Pipelines with an NVIDIA GPU that need long scanned or rendered documents parsed in one pass, with page order, cross-page tables and boxes kept", "strengths": [ "Small, 3.3B parameters with about 0.5B active per token, in 6.69 GB of BF16 safetensors", "Reads many pages in one request with cross-page context, merging tables and text that continue across pages", "MIT with nothing added, ungated, files hashed in Baidu's verified organisation", "An OpenAI-compatible server through SGLang with page-window scheduling for long documents, and a documented converter from its block output to Markdown" ], "weaknesses": [ "Loading runs Baidu's code, remote code in Transformers or a prebuilt SGLang fork from the repository, and the save_results path calls eval on model output", "No released runtime runs its sparse attention yet, and no quantised build", "The card states no parameters, languages, context length or limitations, and no safety results or security contact were found", "Every accuracy figure is Baidu's own, one of its two long-document benchmarks is Baidu's own, and no independent result exists for this checkpoint", "Charts and figures come back as boxes to crop, not as data, and the report says heading hierarchy is weak over long documents" ], "agentNotes": [ "Quickest local run, `pip install torch==2.13.0 torchvision pillow transformers==4.52.1 huggingface-hub==0.36.0 tokenizers==0.21.4 addict==2.4.0 einops==0.8.2 easydict==1.13`, then `AutoModel.from_pretrained(\"baidu/Unlimited-OCR-2\", trust_remote_code=True, use_safetensors=True, torch_dtype=torch.bfloat16).eval().cuda()` and `model.infer_multi(tokenizer, image_files=pages, output_path=\"out\")`", "To serve it, download the repository, install `wheel/sglang-0.5.20.dev10+g8d62f5fb9c-py3-none-any.whl` with pymupdf and fastokens in a Python 3.10 venv, and start `python -m sglang.launch_server --model-path baidu/Unlimited-OCR-2 --chat-template unlimited-ocr --enable-custom-logit-processor --enable-streaming-session --disable-radix-cache --mem-fraction-static 0.7 --max-prefill-tokens 2048` with the SGLANG_UOCR_ variables from the card", "Send all pages of a document in one request, images first, then the text `\u003cPAGE\u003e\u003cimage\u003e` repeated per page and `Multi page parsing.`, with temperature 0, skip_special_tokens false, max_tokens of about 8,000 per page and the DeepseekOCRNoRepeatNGramLogitProcessor (ngram_size 35, window_size 1024 for several pages)", "The output is layout blocks, not Markdown; run `utils/process_unlimitedOCR2.py` from github.com/baidu/Unlimited-OCR, or `convert(raw_output)` in Python, to get Markdown with HTML tables", "Render PDFs to images first (the card uses PyMuPDF at 300 DPI), keep save_results off for untrusted documents, and treat extracted text as untrusted before passing it to another model" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.5 } ], "editorialScores": { "interface": 75, "reach": 55, "risk": 45, "upkeep": 45 }, "provenanceScore": 73, "checked": { "categories": { "interface": "2026-10-27", "reach": "2026-10-27", "risk": "2026-10-27", "upkeep": "2026-10-27" }, "last": "2026-10-27", "oldest": "2026-10-27", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "pip install torch==2.13.0 torchvision pillow transformers==4.52.1 huggingface-hub==0.36.0 tokenizers==0.21.4 addict==2.4.0 einops==0.8.2 easydict==1.13\n# then AutoModel.from_pretrained(\"baidu/Unlimited-OCR-2\", trust_remote_code=True, use_safetensors=True, torch_dtype=torch.bfloat16).eval().cuda()\n# and model.infer_multi(tokenizer, image_files=[\"page_1.jpg\", \"page_2.jpg\"], output_path=\"out\")", "http": "# after: hf download baidu/Unlimited-OCR-2 --local-dir uocr2 \u0026\u0026 uv venv --python 3.10 \u0026\u0026 . .venv/bin/activate\n# uv pip install uocr2/wheel/sglang-0.5.20.dev10+g8d62f5fb9c-py3-none-any.whl pymupdf==1.27.2.2 fastokens==0.3.2\n# SGLANG_UOCR_EANABLE_DOC_LIMIT=1 python -m sglang.launch_server --model-path baidu/Unlimited-OCR-2 --served-model-name Unlimited-OCR-2 --chat-template unlimited-ocr --tokenizer-backend fastokens --mem-fraction-static 0.7 --max-prefill-tokens 2048 --enable-custom-logit-processor --enable-streaming-session --disable-radix-cache --port 10000\ncurl http://127.0.0.1:10000/v1/chat/completions -H 'Content-Type: application/json' -d '{\"model\":\"Unlimited-OCR-2\",\"temperature\":0,\"max_tokens\":8000,\"skip_special_tokens\":false,\"images_config\":{\"crop_mode\":true},\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"image_url\",\"image_url\":{\"url\":\"data:image/png;base64,...\"}},{\"type\":\"text\",\"text\":\"\u003cPAGE\u003e\u003cimage\u003eMulti page parsing.\"}]}]}'" }, "letme": { "capability": "https://letme.dev/docs.ocr", "tool": "https://letme.dev/unlimited-ocr-2" }, "weights": { "trainedBy": "Baidu (ERNIE Team)", "builtOn": "baidu/Unlimited-OCR (post-trained from its checkpoint per the report, MIT by its metadata), whose backbone is deepseek-ai/DeepSeek-OCR (MIT by its metadata); not declared in the card's metadata", "params": "3.3B (3B-A0.5B mixture-of-experts decoder per the report)", "context": 131072, "goodFor": "Parsing long scanned or rendered documents, tens to hundreds of pages, into ordered layout blocks with boxes and HTML tables in one request, on an NVIDIA GPU, if Baidu's own results hold up.", "runtimes": [], "builds": [ { "name": "Unlimited-OCR-2 (BF16 safetensors)", "url": "https://huggingface.co/baidu/Unlimited-OCR-2", "who": "publisher", "precision": "bf16", "sizeGB": 6.69, "memoryGB": 12, "format": "safetensors", "runsOn": [ "Transformers (remote code)", "SGLang (Baidu's customised wheel)" ], "note": "Two shards, 6,688,305,576 bytes, so 6.69 GB × 1.2 = 8.03 GB, within 12 GB. The whole repository is 6.87 GB with the report, the wheel and a 156 MB GIF, which comes to the same band. The only build from Baidu; no copy by anyone else exists yet" } ], "run": "hf download baidu/Unlimited-OCR-2 --local-dir uocr2 \u0026\u0026 uv venv --python 3.10 \u0026\u0026 . .venv/bin/activate \u0026\u0026 uv pip install uocr2/wheel/sglang-0.5.20.dev10+g8d62f5fb9c-py3-none-any.whl pymupdf==1.27.2.2 fastokens==0.3.2 \u0026\u0026 SGLANG_UOCR_EANABLE_DOC_LIMIT=1 SGLANG_UOCR_DOC_GUNDAM_PAGE_WINDOW=10 SGLANG_UOCR_DOC_BASE_PAGE_WINDOW=10 SGLANG_UOCR_MAX_PAGE_TOKENS=20000 python -m sglang.launch_server --model-path baidu/Unlimited-OCR-2 --served-model-name Unlimited-OCR-2 --chat-template unlimited-ocr --tokenizer-backend fastokens --mem-fraction-static 0.7 --max-prefill-tokens 2048 --enable-custom-logit-processor --enable-streaming-session --allow-auto-truncate --disable-radix-cache --port 10000", "runBuild": "Unlimited-OCR-2 (BF16 safetensors)", "checked": "2026-10-27", "minMemoryGB": 12 }, "family": { "lab": "Baidu", "family": "Unlimited OCR 2", "url": "https://www.anchorterminal.com/open-weights/#baidu", "olderCount": 1 }, "area": "models", "provenance": { "legalEntity": "Baidu, Inc.", "domain": "baidu.com", "domainRegistered": "1999-10-11", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/baidu/Unlimited-OCR-2/commits/main", "securityTxt": "unknown", "checked": "2026-10-27", "notes": [ "The files sit in Baidu's verified baidu organisation on Hugging Face, which Baidu's GitHub organisation profile links to, and the GitHub code repository's README links this repository. The report's byline is the Baidu ERNIE Team. The legal entity is the card's Baidu Inc., not checked against a registry. The domain registration date is from Verisign's RDAP record for baidu.com, read 2026-10-27.", "Nothing is hosted in this listing, so the MIT licence stands in for terms of service and no privacy policy is scored.", "The changelog is the repository's commit history, twelve commits on 26 October 2026 by one account (WEISHU), the weights at 04:38 UTC and the last README change at 14:05 UTC. The card's release line dates the release 27 October 2026.", "www.baidu.com's robots.txt disallows every path to all agents not named in it, so its security.txt is not read for this listing, and bsrc.baidu.com answered Access denied to its robots.txt. No security contact is named on the card or in the GitHub repository." ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/unlimited-ocr-2.json", "live": { "slug": "unlimited-ocr-2", "securityTxt": { "url": "https://baidu.com/.well-known/security.txt", "state": "none", "checkedAt": "2026-10-27T15:32:20.71581076Z" }, "updatedAt": "2026-10-27T15:32:20.71581076Z" } }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Nanbeige LLM Lab (BOSS Zhipin)", "b": "Baidu", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0 (Hub metadata only; the repository has no LICENSE file)", "b": "MIT (Hub metadata; the Hugging Face repository has no LICENSE file, and the GitHub code repository's LICENSE is the MIT text, copyright 2026 Baidu)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-10-24", "b": "2026-10-26", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" } ], "faq": [ { "answer": "Nanbeige4.3-33B scores 61 (C) on agent readiness against Baidu Unlimited-OCR-2's 53.5 (D), and leads in 3 of 4 scored categories.", "question": "Which is better for AI agents, Nanbeige4.3-33B or Baidu Unlimited-OCR-2?" } ], "goodFor": [ { "aheadOn": [ "Risk, 60 against 45", "Agent interface, 85 against 75", "Documentation and upkeep, 56 against 45" ], "also": null, "goodFor": "Agents with about 96 GB of GPU memory, or the 128 GB reference machine, that want an Apache-tagged 33B model for long coding and tool loops and can wait for independent results.", "slug": "nanbeige-4-3-33b", "watchFor": "No independent benchmark result yet; every agentic number on the card is Nanbeige's own run" }, { "aheadOn": null, "also": null, "goodFor": "Pipelines with an NVIDIA GPU that need long scanned or rendered documents parsed in one pass, with page order, cross-page tables and boxes kept", "slug": "unlimited-ocr-2", "watchFor": "Loading runs Baidu's code, remote code in Transformers or a prebuilt SGLang fork from the repository, and the save_results path calls eval on model output" } ], "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-nanbeige-4-3-33b.json", "title": "Agents-A1-4B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-unlimited-ocr-2.json", "title": "Agents-A1-4B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-nanbeige-4-3-33b.json", "title": "Apertus v1.5 8B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-unlimited-ocr-2.json", "title": "Apertus v1.5 8B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-nanbeige-4-3-33b.json", "title": "Apodex-1.1-mini vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-unlimited-ocr-2.json", "title": "Apodex-1.1-mini vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-nanbeige-4-3-33b.json", "title": "BigBang-v1 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-unlimited-ocr-2.json", "title": "BigBang-v1 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-nanbeige-4-3-33b.json", "title": "Carbon-X vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-unlimited-ocr-2.json", "title": "Carbon-X vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-nanbeige-4-3-33b.json", "title": "Cosmos-Reason2-2B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-unlimited-ocr-2.json", "title": "Cosmos-Reason2-2B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-nanbeige-4-3-33b.json", "title": "Darwin-36B-Opus vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-unlimited-ocr-2.json", "title": "Darwin-36B-Opus vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nanbeige-4-3-33b.json", "title": "DeepSeek-V3.2 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-unlimited-ocr-2.json", "title": "DeepSeek-V3.2 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-nanbeige-4-3-33b.json", "title": "DeepSeek V4.1 Flash vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-unlimited-ocr-2.json", "title": "DeepSeek V4.1 Flash vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-nanbeige-4-3-33b.json", "title": "DeepSeek-V4-Flash-0731 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-unlimited-ocr-2.json", "title": "DeepSeek-V4-Flash-0731 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nanbeige-4-3-33b.json", "title": "DiffusionGemma 26B A4B IT vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-unlimited-ocr-2.json", "title": "DiffusionGemma 26B A4B IT vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nanbeige-4-3-33b.json", "title": "Gemma 4 12B IT vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-unlimited-ocr-2.json", "title": "Gemma 4 12B IT vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-nanbeige-4-3-33b.json", "title": "Gemma 4 26B A4B IT vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-unlimited-ocr-2.json", "title": "Gemma 4 26B A4B IT vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-nanbeige-4-3-33b.json", "title": "Gemma 4 31B IT vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-unlimited-ocr-2.json", "title": "Gemma 4 31B IT vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-nanbeige-4-3-33b.json", "title": "Gemma 4 E2B IT vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-unlimited-ocr-2.json", "title": "Gemma 4 E2B IT vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-nanbeige-4-3-33b.json", "title": "Gemma 4 E4B IT vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-unlimited-ocr-2.json", "title": "Gemma 4 E4B IT vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-nanbeige-4-3-33b.json", "title": "GLM-4.5-Air vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-unlimited-ocr-2.json", "title": "GLM-4.5-Air vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-nanbeige-4-3-33b.json", "title": "GLM-4.7-Flash vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-unlimited-ocr-2.json", "title": "GLM-4.7-Flash vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nanbeige-4-3-33b.json", "title": "GLM-5.3-Flash vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-unlimited-ocr-2.json", "title": "GLM-5.3-Flash vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-nanbeige-4-3-33b.json", "title": "GLM-5.3 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-unlimited-ocr-2.json", "title": "GLM-5.3 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-nanbeige-4-3-33b.json", "title": "gpt-oss-120b vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-unlimited-ocr-2.json", "title": "gpt-oss-120b vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nanbeige-4-3-33b.json", "title": "gpt-oss-20b vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-unlimited-ocr-2.json", "title": "gpt-oss-20b vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-nanbeige-4-3-33b.json", "title": "Granite 4.2 3B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-unlimited-ocr-2.json", "title": "Granite 4.2 3B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nanbeige-4-3-33b.json", "title": "Hy3 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/hy3-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-unlimited-ocr-2.json", "title": "Hy3 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/hy3-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/inkling-small-vs-nanbeige-4-3-33b.json", "title": "Inkling-Small vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/inkling-small-vs-unlimited-ocr-2.json", "title": "Inkling-Small vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-3-33b.json", "title": "Inkling vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-unlimited-ocr-2.json", "title": "Inkling vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/inkling-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-nanbeige-4-3-33b.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-unlimited-ocr-2.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-nanbeige-4-3-33b.json", "title": "Kimi K3 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-unlimited-ocr-2.json", "title": "Kimi K3 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-nanbeige-4-3-33b.json", "title": "Kolibri-1 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-unlimited-ocr-2.json", "title": "Kolibri-1 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/kronos-vs-nanbeige-4-3-33b.json", "title": "Kronos vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/kronos-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/kronos-vs-unlimited-ocr-2.json", "title": "Kronos vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/kronos-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/laguna-m-1-vs-nanbeige-4-3-33b.json", "title": "Laguna M.1 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/laguna-m-1-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/laguna-m-1-vs-unlimited-ocr-2.json", "title": "Laguna M.1 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/laguna-m-1-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-nanbeige-4-3-33b.json", "title": "Laguna S 2.1 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-unlimited-ocr-2.json", "title": "Laguna S 2.1 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-nanbeige-4-3-33b.json", "title": "Laguna XS 2.1 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-unlimited-ocr-2.json", "title": "Laguna XS 2.1 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-nanbeige-4-3-33b.json", "title": "LBS-27B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-unlimited-ocr-2.json", "title": "LBS-27B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-nanbeige-4-3-33b.json", "title": "LFM2.5-2.6B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-unlimited-ocr-2.json", "title": "LFM2.5-2.6B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-nanbeige-4-3-33b.json", "title": "Ling-3.0-tiny vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-unlimited-ocr-2.json", "title": "Ling-3.0-tiny vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-nanbeige-4-3-33b.json", "title": "MiMo-V2.6 Distill Qwen 9B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-unlimited-ocr-2.json", "title": "MiMo-V2.6 Distill Qwen 9B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-nanbeige-4-3-33b.json", "title": "MiniCPM-o 4.5 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-unlimited-ocr-2.json", "title": "MiniCPM-o 4.5 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-nanbeige-4-3-33b.json", "title": "MiniCPM5-2B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-unlimited-ocr-2.json", "title": "MiniCPM5-2B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-nanbeige-4-3-33b.json", "title": "MiniMax-M2.5 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-unlimited-ocr-2.json", "title": "MiniMax-M2.5 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-nanbeige-4-3-33b.json", "title": "MiniMax-M2.7 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-unlimited-ocr-2.json", "title": "MiniMax-M2.7 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-nanbeige-4-3-33b.json", "title": "MiniMax-M3.1-Flash vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-unlimited-ocr-2.json", "title": "MiniMax-M3.1-Flash vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-nanbeige-4-3-33b.json", "title": "Muse Glimmer 30B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-unlimited-ocr-2.json", "title": "Muse Glimmer 30B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "Nanbeige4.3-33B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Nanbeige4.3-33B vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-nano-30b-a3b.json", "title": "Nanbeige4.3-33B vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-nano-4b.json", "title": "Nanbeige4.3-33B vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Nanbeige4.3-33B vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-super-120b-a12b.json", "title": "Nanbeige4.3-33B vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-ultra-550b-a55b.json", "title": "Nanbeige4.3-33B vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-occamy-1-0.json", "title": "Nanbeige4.3-33B vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-olmo-3-7b-think.json", "title": "Nanbeige4.3-33B vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ornith-1-5-35b-a3b.json", "title": "Nanbeige4.3-33B vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ornith-1-5-397b.json", "title": "Nanbeige4.3-33B vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ornith-1-5-9b.json", "title": "Nanbeige4.3-33B vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Nanbeige4.3-33B vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-4b-instruct-2507.json", "title": "Nanbeige4.3-33B vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-0-8b.json", "title": "Nanbeige4.3-33B vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-122b-a10b.json", "title": "Nanbeige4.3-33B vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-2b.json", "title": "Nanbeige4.3-33B vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-397b-a17b.json", "title": "Nanbeige4.3-33B vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-4b.json", "title": "Nanbeige4.3-33B vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-9b.json", "title": "Nanbeige4.3-33B vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-6-27b.json", "title": "Nanbeige4.3-33B vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-6-35b-a3b.json", "title": "Nanbeige4.3-33B vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-8-27b.json", "title": "Nanbeige4.3-33B vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-8-flash-next.json", "title": "Nanbeige4.3-33B vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Nanbeige4.3-33B vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-coder-next.json", "title": "Nanbeige4.3-33B vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Nanbeige4.3-33B vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-2b-instruct.json", "title": "Nanbeige4.3-33B vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Nanbeige4.3-33B vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-32b-instruct.json", "title": "Nanbeige4.3-33B vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-4b-instruct.json", "title": "Nanbeige4.3-33B vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-8b-instruct.json", "title": "Nanbeige4.3-33B vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwopus3-8-27b-flash-v2.json", "title": "Nanbeige4.3-33B vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-recursive-flint.json", "title": "Nanbeige4.3-33B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-smollm3-3b.json", "title": "Nanbeige4.3-33B vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-spark-x2-6-4b.json", "title": "Nanbeige4.3-33B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-swift-1-5-qwen3-8-27b.json", "title": "Nanbeige4.3-33B vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Nanbeige4.3-33B vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-thinkingcap-qwen3-8-27b.json", "title": "Nanbeige4.3-33B vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-unlimited-ocr-2.json", "title": "NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-unlimited-ocr-2.json", "title": "Nemotron 3.5 Lightning 30B A3B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-unlimited-ocr-2.json", "title": "Nemotron 3 Nano 30B A3B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-unlimited-ocr-2.json", "title": "Nemotron 3 Nano 4B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-unlimited-ocr-2.json", "title": "Nemotron 3 Super 120B A12B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-unlimited-ocr-2.json", "title": "Nemotron 3 Ultra 550B A55B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/occamy-1-0-vs-unlimited-ocr-2.json", "title": "occamy-1.0 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/occamy-1-0-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-unlimited-ocr-2.json", "title": "Olmo 3 7B Think vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-unlimited-ocr-2.json", "title": "Ornith-1.5-35B-A3B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-unlimited-ocr-2.json", "title": "Ornith-1.5-397B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-unlimited-ocr-2.json", "title": "Ornith-1.5-9B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-unlimited-ocr-2.json", "title": "Qwen3-30B-A3B-Instruct-2507 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-unlimited-ocr-2.json", "title": "Qwen3-4B-Instruct-2507 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-unlimited-ocr-2.json", "title": "Qwen3.5-0.8B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-unlimited-ocr-2.json", "title": "Qwen3.5-122B-A10B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-2b-vs-unlimited-ocr-2.json", "title": "Qwen3.5-2B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-5-2b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-unlimited-ocr-2.json", "title": "Qwen3.5-397B-A17B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-4b-vs-unlimited-ocr-2.json", "title": "Qwen3.5-4B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-5-4b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-9b-vs-unlimited-ocr-2.json", "title": "Qwen3.5-9B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-5-9b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-6-27b-vs-unlimited-ocr-2.json", "title": "Qwen3.6-27B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-6-27b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-unlimited-ocr-2.json", "title": "Qwen3.6-35B-A3B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-8-27b-vs-unlimited-ocr-2.json", "title": "Qwen3.8-27B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-8-27b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-unlimited-ocr-2.json", "title": "Qwen3.8-Flash-Next vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-unlimited-ocr-2.json", "title": "Qwen3-Coder-30B-A3B-Instruct vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-coder-next-vs-unlimited-ocr-2.json", "title": "Qwen3-Coder-Next vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-coder-next-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-unlimited-ocr-2.json", "title": "Qwen3-VL-2B-Instruct vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-unlimited-ocr-2.json", "title": "Qwen3-VL-30B-A3B-Instruct vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-unlimited-ocr-2.json", "title": "Qwen3-VL-32B-Instruct vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-unlimited-ocr-2.json", "title": "Qwen3-VL-4B-Instruct vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-unlimited-ocr-2.json", "title": "Qwen3-VL-8B-Instruct vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-unlimited-ocr-2.json", "title": "Qwopus3.8-27B-Flash-V2 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/recursive-flint-vs-unlimited-ocr-2.json", "title": "Recursive Flint vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/recursive-flint-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/smollm3-3b-vs-unlimited-ocr-2.json", "title": "SmolLM3-3B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/smollm3-3b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-unlimited-ocr-2.json", "title": "Spark-X2.6-4B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/swift-1-5-qwen3-8-27b-vs-unlimited-ocr-2.json", "title": "Swift 1.5 Qwen3.8-27B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/swift-1-5-qwen3-8-27b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/swift-1-5-qwen3-8-flash-next-vs-unlimited-ocr-2.json", "title": "Swift 1.5 Qwen3.8-Flash-Next vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/swift-1-5-qwen3-8-flash-next-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/thinkingcap-qwen3-8-27b-vs-unlimited-ocr-2.json", "title": "ThinkingCap (Qwen3.8 27B) vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/thinkingcap-qwen3-8-27b-vs-unlimited-ocr-2" } ], "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 0, "edge": "", "key": "reach", "name": "Reach", "nanbeige-4-3-33b": 55, "unlimited-ocr-2": 55, "weight": 25 }, { "by": 15, "edge": "nanbeige-4-3-33b", "key": "risk", "name": "Risk", "nanbeige-4-3-33b": 60, "unlimited-ocr-2": 45, "weight": 20 }, { "by": 10, "edge": "nanbeige-4-3-33b", "key": "interface", "name": "Agent interface", "nanbeige-4-3-33b": 85, "unlimited-ocr-2": 75, "weight": 10 }, { "by": 11, "edge": "nanbeige-4-3-33b", "key": "upkeep", "name": "Documentation and upkeep", "nanbeige-4-3-33b": 56, "unlimited-ocr-2": 45, "weight": 10 } ], "summary": "Nanbeige4.3-33B scores 61 (C) on agent readiness against Baidu Unlimited-OCR-2's 53.5 (D), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.", "tutorials": [], "verdicts": { "nanbeige-4-3-33b": "A dense 33B Llama-architecture cousin for long agentic coding and office tasks, with per-request thinking, XML tool calls that stock vLLM and SGLang parse, and 512K of context. It needs about 96 GB at BF16, as Nanbeige ships no quantised build. Its agentic results so far are Nanbeige's own, with no safety results, training data notes or licence file.", "unlimited-ocr-2": "A small MIT document-parsing cousin that reads up to hundreds of pages in one request and returns ordered layout blocks with boxes and HTML tables. It needs an NVIDIA GPU with about 12 GB, through Baidu's remote code or its own SGLang build. The risks are running the publisher's code and accuracy figures that are Baidu's own." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-unlimited-ocr-2", "json": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-unlimited-ocr-2.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-unlimited-ocr-2.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-unlimited-ocr-2.min.md" }, "markdown": "Nanbeige4.3-33B scores 61 (C) on agent readiness against Baidu Unlimited-OCR-2's 53.5 (D), and leads in 3 of 4 scored categories. Both do open-weight models you run yourself.\n\n- Nanbeige4.3-33B: grade C, 61/100, rank #56 of 113 open-weight models. Markdown https://www.anchorterminal.com/tools/nanbeige-4-3-33b.md · JSON https://www.anchorterminal.com/api/v1/tools/nanbeige-4-3-33b.json\n- Baidu Unlimited-OCR-2: grade D, 53.5/100, rank #92 of 113 open-weight models. Markdown https://www.anchorterminal.com/tools/unlimited-ocr-2.md · JSON https://www.anchorterminal.com/api/v1/tools/unlimited-ocr-2.json\n- Best open-weight models you download and run yourself for AI agents: https://www.anchorterminal.com/best/open-weights/index.md\n- All 3504 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### Nanbeige4.3-33B (C)\n\nGood for: Agents with about 96 GB of GPU memory, or the 128 GB reference machine, that want an Apache-tagged 33B model for long coding and tool loops and can wait for independent results.\n\nAhead on:\n- Risk, 60 against 45\n- Agent interface, 85 against 75\n- Documentation and upkeep, 56 against 45\n\nWatch for: No independent benchmark result yet; every agentic number on the card is Nanbeige's own run\n\n### Baidu Unlimited-OCR-2 (D)\n\nGood for: Pipelines with an NVIDIA GPU that need long scanned or rendered documents parsed in one pass, with page order, cross-page tables and boxes kept\n\nWatch for: Loading runs Baidu's code, remote code in Transformers or a prebuilt SGLang fork from the repository, and the save_results path calls eval on model output\n\n\n## Score by category\n\n| Category | Weight | Nanbeige4.3-33B | Baidu Unlimited-OCR-2 | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 55 | 55 | even |\n| Risk | 20% (20 this run) | 60 | 45 | Nanbeige4.3-33B +15 |\n| Agent interface | 10% (10 this run) | 85 | 75 | Nanbeige4.3-33B +10 |\n| Documentation and upkeep | 10% (10 this run) | 56 | 45 | Nanbeige4.3-33B +11 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **61 · C** | **53.5 · D** | |\n\n## Facts side by side\n\n| Fact | Nanbeige4.3-33B | Baidu Unlimited-OCR-2 |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Nanbeige LLM Lab (BOSS Zhipin) | Baidu |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 (Hub metadata only; the repository has no LICENSE file) | MIT (Hub metadata; the Hugging Face repository has no LICENSE file, and the GitHub code repository's LICENSE is the MIT text, copyright 2026 Baidu) |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-10-24 | 2026-10-26 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n\n## Verdicts\n\n**Nanbeige4.3-33B.** A dense 33B Llama-architecture cousin for long agentic coding and office tasks, with per-request thinking, XML tool calls that stock vLLM and SGLang parse, and 512K of context. It needs about 96 GB at BF16, as Nanbeige ships no quantised build. Its agentic results so far are Nanbeige's own, with no safety results, training data notes or licence file.\n\n**Baidu Unlimited-OCR-2.** A small MIT document-parsing cousin that reads up to hundreds of pages in one request and returns ordered layout blocks with boxes and HTML tables. It needs an NVIDIA GPU with about 12 GB, through Baidu's remote code or its own SGLang build. The risks are running the publisher's code and accuracy figures that are Baidu's own.\n\n## Before you call either\n\n### Nanbeige4.3-33B\n\n1. Serve with `vllm serve Nanbeige/Nanbeige4.3-33B --enable-auto-tool-choice --reasoning-parser qwen3 --tool-call-parser qwen3_coder`, as the card says, or SGLang with the same two parsers\n2. Keep `tool_call_format` at its default `xml`, since qwen3_coder parses that format; the `json` option writes Hermes-style JSON calls, which need a different parser such as vLLM's hermes\n3. Pass `chat_template_kwargs` `{\"preserve_thinking\": true}` for multi-turn tool use and coding, and `{\"enable_thinking\": false}` to skip reasoning, as the card recommends\n4. Use temperature 1.0, top_p 0.95 and up to 65,536 new tokens for agent work, and temperature 0.6 for reasoning and chat, per the card\n5. Send your own system prompt, since without one the template injects a Chinese identity line, or a Chinese tool-expert prompt when tools are passed\n6. Send one system message at the start only, as the template raises an error for a later one\n7. In plain Transformers pass `use_cache=True` to generate, since config.json and generation_config.json set it false; trust_remote_code isn't needed\n\n### Baidu Unlimited-OCR-2\n\n1. Quickest local run, `pip install torch==2.13.0 torchvision pillow transformers==4.52.1 huggingface-hub==0.36.0 tokenizers==0.21.4 addict==2.4.0 einops==0.8.2 easydict==1.13`, then `AutoModel.from_pretrained(\"baidu/Unlimited-OCR-2\", trust_remote_code=True, use_safetensors=True, torch_dtype=torch.bfloat16).eval().cuda()` and `model.infer_multi(tokenizer, image_files=pages, output_path=\"out\")`\n2. To serve it, download the repository, install `wheel/sglang-0.5.20.dev10+g8d62f5fb9c-py3-none-any.whl` with pymupdf and fastokens in a Python 3.10 venv, and start `python -m sglang.launch_server --model-path baidu/Unlimited-OCR-2 --chat-template unlimited-ocr --enable-custom-logit-processor --enable-streaming-session --disable-radix-cache --mem-fraction-static 0.7 --max-prefill-tokens 2048` with the SGLANG_UOCR_ variables from the card\n3. Send all pages of a document in one request, images first, then the text `\u003cPAGE\u003e\u003cimage\u003e` repeated per page and `Multi page parsing.`, with temperature 0, skip_special_tokens false, max_tokens of about 8,000 per page and the DeepseekOCRNoRepeatNGramLogitProcessor (ngram_size 35, window_size 1024 for several pages)\n4. The output is layout blocks, not Markdown; run `utils/process_unlimitedOCR2.py` from github.com/baidu/Unlimited-OCR, or `convert(raw_output)` in Python, to get Markdown with HTML tables\n5. Render PDFs to images first (the card uses PyMuPDF at 300 DPI), keep save_results off for untrusted documents, and treat extracted text as untrusted before passing it to another model\n\n## Questions\n\n### Which is better for AI agents, Nanbeige4.3-33B or Baidu Unlimited-OCR-2?\n\nNanbeige4.3-33B scores 61 (C) on agent readiness against Baidu Unlimited-OCR-2's 53.5 (D), and leads in 3 of 4 scored categories.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-unlimited-ocr-2.json, and with the fewest tokens: https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-unlimited-ocr-2.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"nanbeige-4-3-33b\", \"b\": \"unlimited-ocr-2\"}`. From a terminal: `anchor compare nanbeige-4-3-33b unlimited-ocr-2`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/nanbeige-4-3-33b.json and https://www.anchorterminal.com/api/v1/tools/unlimited-ocr-2.json\n\n## Other comparisons with Nanbeige4.3-33B or Baidu Unlimited-OCR-2\n\n- [Agents-A1-4B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/agents-a1-4b-vs-nanbeige-4-3-33b.md)\n- [Agents-A1-4B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/agents-a1-4b-vs-unlimited-ocr-2.md)\n- [Apertus v1.5 8B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-nanbeige-4-3-33b.md)\n- [Apertus v1.5 8B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-unlimited-ocr-2.md)\n- [Apodex-1.1-mini vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-nanbeige-4-3-33b.md)\n- [Apodex-1.1-mini vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-unlimited-ocr-2.md)\n- [BigBang-v1 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/bigbang-v1-vs-nanbeige-4-3-33b.md)\n- [BigBang-v1 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/bigbang-v1-vs-unlimited-ocr-2.md)\n- [Carbon-X vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/carbon-x-vs-nanbeige-4-3-33b.md)\n- [Carbon-X vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/carbon-x-vs-unlimited-ocr-2.md)\n- [Cosmos-Reason2-2B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-nanbeige-4-3-33b.md)\n- [Cosmos-Reason2-2B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-unlimited-ocr-2.md)\n- [Darwin-36B-Opus vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-nanbeige-4-3-33b.md)\n- [Darwin-36B-Opus vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-unlimited-ocr-2.md)\n- [DeepSeek-V3.2 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-nanbeige-4-3-33b.md)\n- [DeepSeek-V3.2 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-unlimited-ocr-2.md)\n- [DeepSeek V4.1 Flash vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-nanbeige-4-3-33b.md)\n- [DeepSeek V4.1 Flash vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-unlimited-ocr-2.md)\n- [DeepSeek-V4-Flash-0731 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-nanbeige-4-3-33b.md)\n- [DeepSeek-V4-Flash-0731 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-unlimited-ocr-2.md)\n- [DiffusionGemma 26B A4B IT vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-nanbeige-4-3-33b.md)\n- [DiffusionGemma 26B A4B IT vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-unlimited-ocr-2.md)\n- [Gemma 4 12B IT vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-nanbeige-4-3-33b.md)\n- [Gemma 4 12B IT vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-unlimited-ocr-2.md)\n- [Gemma 4 26B A4B IT vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-nanbeige-4-3-33b.md)\n- [Gemma 4 26B A4B IT vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-unlimited-ocr-2.md)\n- [Gemma 4 31B IT vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-nanbeige-4-3-33b.md)\n- [Gemma 4 31B IT vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-unlimited-ocr-2.md)\n- [Gemma 4 E2B IT vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-nanbeige-4-3-33b.md)\n- [Gemma 4 E2B IT vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-unlimited-ocr-2.md)\n- [Gemma 4 E4B IT vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-nanbeige-4-3-33b.md)\n- [Gemma 4 E4B IT vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-unlimited-ocr-2.md)\n- [GLM-4.5-Air vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/glm-4-5-air-vs-nanbeige-4-3-33b.md)\n- [GLM-4.5-Air vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/glm-4-5-air-vs-unlimited-ocr-2.md)\n- [GLM-4.7-Flash vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-nanbeige-4-3-33b.md)\n- [GLM-4.7-Flash vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-unlimited-ocr-2.md)\n- [GLM-5.3-Flash vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-nanbeige-4-3-33b.md)\n- [GLM-5.3-Flash vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-unlimited-ocr-2.md)\n- [GLM-5.3 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/glm-5-3-vs-nanbeige-4-3-33b.md)\n- [GLM-5.3 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/glm-5-3-vs-unlimited-ocr-2.md)\n- [gpt-oss-120b vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-nanbeige-4-3-33b.md)\n- [gpt-oss-120b vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-unlimited-ocr-2.md)\n- [gpt-oss-20b vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-nanbeige-4-3-33b.md)\n- [gpt-oss-20b vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-unlimited-ocr-2.md)\n- [Granite 4.2 3B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-nanbeige-4-3-33b.md)\n- [Granite 4.2 3B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-unlimited-ocr-2.md)\n- [Hy3 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/hy3-vs-nanbeige-4-3-33b.md)\n- [Hy3 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/hy3-vs-unlimited-ocr-2.md)\n- [Inkling-Small vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/inkling-small-vs-nanbeige-4-3-33b.md)\n- [Inkling-Small vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/inkling-small-vs-unlimited-ocr-2.md)\n- [Inkling vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-3-33b.md)\n- [Inkling vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/inkling-vs-unlimited-ocr-2.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-nanbeige-4-3-33b.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-unlimited-ocr-2.md)\n- [Kimi K3 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/kimi-k3-vs-nanbeige-4-3-33b.md)\n- [Kimi K3 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/kimi-k3-vs-unlimited-ocr-2.md)\n- [Kolibri-1 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/kolibri-1-vs-nanbeige-4-3-33b.md)\n- [Kolibri-1 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/kolibri-1-vs-unlimited-ocr-2.md)\n- [Kronos vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/kronos-vs-nanbeige-4-3-33b.md)\n- [Kronos vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/kronos-vs-unlimited-ocr-2.md)\n- [Laguna M.1 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/laguna-m-1-vs-nanbeige-4-3-33b.md)\n- [Laguna M.1 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/laguna-m-1-vs-unlimited-ocr-2.md)\n- [Laguna S 2.1 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-nanbeige-4-3-33b.md)\n- [Laguna S 2.1 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-unlimited-ocr-2.md)\n- [Laguna XS 2.1 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-nanbeige-4-3-33b.md)\n- [Laguna XS 2.1 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-unlimited-ocr-2.md)\n- [LBS-27B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/lbs-27b-vs-nanbeige-4-3-33b.md)\n- [LBS-27B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/lbs-27b-vs-unlimited-ocr-2.md)\n- [LFM2.5-2.6B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-nanbeige-4-3-33b.md)\n- [LFM2.5-2.6B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-unlimited-ocr-2.md)\n- [Ling-3.0-tiny vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-nanbeige-4-3-33b.md)\n- [Ling-3.0-tiny vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-unlimited-ocr-2.md)\n- [MiMo-V2.6 Distill Qwen 9B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-nanbeige-4-3-33b.md)\n- [MiMo-V2.6 Distill Qwen 9B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-unlimited-ocr-2.md)\n- [MiniCPM-o 4.5 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-nanbeige-4-3-33b.md)\n- [MiniCPM-o 4.5 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-unlimited-ocr-2.md)\n- [MiniCPM5-2B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/minicpm5-2b-vs-nanbeige-4-3-33b.md)\n- [MiniCPM5-2B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/minicpm5-2b-vs-unlimited-ocr-2.md)\n- [MiniMax-M2.5 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/minimax-m2-5-vs-nanbeige-4-3-33b.md)\n- [MiniMax-M2.5 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/minimax-m2-5-vs-unlimited-ocr-2.md)\n- [MiniMax-M2.7 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/minimax-m2-7-vs-nanbeige-4-3-33b.md)\n- [MiniMax-M2.7 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/minimax-m2-7-vs-unlimited-ocr-2.md)\n- [MiniMax-M3.1-Flash vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-nanbeige-4-3-33b.md)\n- [MiniMax-M3.1-Flash vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/minimax-m3-1-flash-vs-unlimited-ocr-2.md)\n- [Muse Glimmer 30B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-nanbeige-4-3-33b.md)\n- [Muse Glimmer 30B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-unlimited-ocr-2.md)\n- [Nanbeige4.3-33B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Nanbeige4.3-33B vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Nanbeige4.3-33B vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-nano-30b-a3b.md)\n- [Nanbeige4.3-33B vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-nano-4b.md)\n- [Nanbeige4.3-33B vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Nanbeige4.3-33B vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-super-120b-a12b.md)\n- [Nanbeige4.3-33B vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-nemotron-3-ultra-550b-a55b.md)\n- [Nanbeige4.3-33B vs occamy-1.0](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-occamy-1-0.md)\n- [Nanbeige4.3-33B vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-olmo-3-7b-think.md)\n- [Nanbeige4.3-33B vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ornith-1-5-35b-a3b.md)\n- [Nanbeige4.3-33B vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ornith-1-5-397b.md)\n- [Nanbeige4.3-33B vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-ornith-1-5-9b.md)\n- [Nanbeige4.3-33B vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Nanbeige4.3-33B vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-4b-instruct-2507.md)\n- [Nanbeige4.3-33B vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-0-8b.md)\n- [Nanbeige4.3-33B vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-122b-a10b.md)\n- [Nanbeige4.3-33B vs Qwen3.5-2B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-2b.md)\n- [Nanbeige4.3-33B vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-397b-a17b.md)\n- [Nanbeige4.3-33B vs Qwen3.5-4B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-4b.md)\n- [Nanbeige4.3-33B vs Qwen3.5-9B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-5-9b.md)\n- [Nanbeige4.3-33B vs Qwen3.6-27B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-6-27b.md)\n- [Nanbeige4.3-33B vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-6-35b-a3b.md)\n- [Nanbeige4.3-33B vs Qwen3.8-27B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-8-27b.md)\n- [Nanbeige4.3-33B vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-8-flash-next.md)\n- [Nanbeige4.3-33B vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Nanbeige4.3-33B vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-coder-next.md)\n- [Nanbeige4.3-33B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Nanbeige4.3-33B vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-2b-instruct.md)\n- [Nanbeige4.3-33B vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Nanbeige4.3-33B vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-32b-instruct.md)\n- [Nanbeige4.3-33B vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-4b-instruct.md)\n- [Nanbeige4.3-33B vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwen3-vl-8b-instruct.md)\n- [Nanbeige4.3-33B vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-qwopus3-8-27b-flash-v2.md)\n- [Nanbeige4.3-33B vs Recursive Flint](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-recursive-flint.md)\n- [Nanbeige4.3-33B vs SmolLM3-3B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-smollm3-3b.md)\n- [Nanbeige4.3-33B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-spark-x2-6-4b.md)\n- [Nanbeige4.3-33B vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-swift-1-5-qwen3-8-27b.md)\n- [Nanbeige4.3-33B vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Nanbeige4.3-33B vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-thinkingcap-qwen3-8-27b.md)\n- [NVIDIA Nemotron 3.5 Bolt E4B 4GB vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/nemotron-3-5-bolt-e4b-4gb-vs-unlimited-ocr-2.md)\n- [Nemotron 3.5 Lightning 30B A3B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-unlimited-ocr-2.md)\n- [Nemotron 3 Nano 30B A3B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-unlimited-ocr-2.md)\n- [Nemotron 3 Nano 4B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-unlimited-ocr-2.md)\n- [Nemotron 3 Super 120B A12B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-unlimited-ocr-2.md)\n- [Nemotron 3 Ultra 550B A55B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-unlimited-ocr-2.md)\n- [occamy-1.0 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/occamy-1-0-vs-unlimited-ocr-2.md)\n- [Olmo 3 7B Think vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-unlimited-ocr-2.md)\n- [Ornith-1.5-35B-A3B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-unlimited-ocr-2.md)\n- [Ornith-1.5-397B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-unlimited-ocr-2.md)\n- [Ornith-1.5-9B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-unlimited-ocr-2.md)\n- [Qwen3-30B-A3B-Instruct-2507 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-unlimited-ocr-2.md)\n- [Qwen3-4B-Instruct-2507 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-unlimited-ocr-2.md)\n- [Qwen3.5-0.8B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-unlimited-ocr-2.md)\n- [Qwen3.5-122B-A10B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-unlimited-ocr-2.md)\n- [Qwen3.5-2B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-5-2b-vs-unlimited-ocr-2.md)\n- [Qwen3.5-397B-A17B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-unlimited-ocr-2.md)\n- [Qwen3.5-4B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-5-4b-vs-unlimited-ocr-2.md)\n- [Qwen3.5-9B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-5-9b-vs-unlimited-ocr-2.md)\n- [Qwen3.6-27B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-6-27b-vs-unlimited-ocr-2.md)\n- [Qwen3.6-35B-A3B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-unlimited-ocr-2.md)\n- [Qwen3.8-27B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-8-27b-vs-unlimited-ocr-2.md)\n- [Qwen3.8-Flash-Next vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-unlimited-ocr-2.md)\n- [Qwen3-Coder-30B-A3B-Instruct vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-unlimited-ocr-2.md)\n- [Qwen3-Coder-Next vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-coder-next-vs-unlimited-ocr-2.md)\n- [Qwen3-VL-2B-Instruct vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-unlimited-ocr-2.md)\n- [Qwen3-VL-30B-A3B-Instruct vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-unlimited-ocr-2.md)\n- [Qwen3-VL-32B-Instruct vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-unlimited-ocr-2.md)\n- [Qwen3-VL-4B-Instruct vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-unlimited-ocr-2.md)\n- [Qwen3-VL-8B-Instruct vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-unlimited-ocr-2.md)\n- [Qwopus3.8-27B-Flash-V2 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-unlimited-ocr-2.md)\n- [Recursive Flint vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/recursive-flint-vs-unlimited-ocr-2.md)\n- [SmolLM3-3B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/smollm3-3b-vs-unlimited-ocr-2.md)\n- [Spark-X2.6-4B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-unlimited-ocr-2.md)\n- [Swift 1.5 Qwen3.8-27B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/swift-1-5-qwen3-8-27b-vs-unlimited-ocr-2.md)\n- [Swift 1.5 Qwen3.8-Flash-Next vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/swift-1-5-qwen3-8-flash-next-vs-unlimited-ocr-2.md)\n- [ThinkingCap (Qwen3.8 27B) vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/thinkingcap-qwen3-8-27b-vs-unlimited-ocr-2.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-27", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Nanbeige4.3-33B vs Baidu Unlimited-OCR-2", "url": "" } ], "description": "Nanbeige4.3-33B scores 61 (C) to Baidu Unlimited-OCR-2's 53.5 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Nanbeige4.3-33B C 61", "Baidu Unlimited-OCR-2 D 53.5", "scores" ], "h1": "Nanbeige4.3-33B vs Baidu Unlimited-OCR-2", "image": "https://www.anchorterminal.com/assets/og/compare-nanbeige-4-3-33b-vs-unlimited-ocr-2.png", "path": "/compare/nanbeige-4-3-33b-vs-unlimited-ocr-2", "published": "2026-10-01", "section": "tools", "title": "Nanbeige4.3-33B vs Baidu Unlimited-OCR-2 for AI agents (2026)", "toc": null, "updated": "2026-10-27", "url": "https://www.anchorterminal.com/compare/nanbeige-4-3-33b-vs-unlimited-ocr-2" }, "tokens": { "markdown": 7000, "slim": 480 }, "version": 1 }