Nutrient document API comparisons
Published by NutrientUpdated

LlamaParse alternatives

Verdict

LlamaParse is a proprietary hosted parser with 130-plus input formats, tiers from 1 to 45 credits per page at $1.25 per 1,000 credits, schema extraction with confidence and citations, and 10,000 free credits. People look for alternatives when they want open source, a per-page USD price, a different accuracy and cost trade-off on scans, or a different deployment boundary.

Choose Docling for free local parsing under MIT. Choose Marker or Datalab for a benchmark-led converter with a hosted API, keeping its model license in mind. Choose Reducto for list prices per 1,000 pages and deployment up to air-gapped. Choose Extend for a workflow platform. Choose Nutrient Data Extraction for a mode ladder that keeps born-digital pages at 1 credit, an Auto mode that picks the mode per page, grounded extraction with match labels, and a free plan that renews 5,000 credits a month. Nutrient was founded as PSPDFKit in 2011. 3,000-plus organizations, including 15 percent of the Global 500, rely on it, with over a billion document interactions a year. The same extraction engine runs hosted, self-hosted in the Python and Java SDKs with no external API calls for OCR and ICR, or on a Mac in Extract Studio.

At a glance

LlamaParse (LlamaCloud), Reducto, Extend, Docling (IBM Research / LF AI & Data), Marker (open source) and Datalab API, Nutrient Data Extraction API; facts fetched 2026-10-15 to 2026-10-16
FactLlamaParse (LlamaCloud)ReductoExtendDocling (IBM Research / LF AI & Data)Marker (open source) and Datalab APINutrient Data Extraction API
Product typehosted API[1]hosted API[2]hosted API[3]open source library[4]both[5]Hosted Data Extraction API, web Studio, and macOS Extract Studio[6]
LicenseProprietary commercial service (LlamaParse); the LlamaIndex framework is MIT and LiteParse Apache-2.0[1]Proprietary closed-source API[7]Proprietary hosted service[8]MIT (codebase). Individual model weights carry their own licenses.[4]Code: Apache-2.0. Model weights: modified AI Pubs Open RAIL-M; free for research, personal use, and companies under $5M funding/revenue (Marker, Surya) or $2M (Chandra); commercial license above that.[5]Proprietary hosted service[9]
Output formatsMarkdown, Plain text, JSON (per-page items), XLSX, HTML tables, Annotated PDF, Structured JSON to custom schema[1]Markdown, JSON, HTML tables[10]Markdown, JSON, HTML tables[11]Markdown, HTML, JSON (lossless DoclingDocument), DocTags, DocLang XML, plain text, WebVTT, chunks JSONL, LaTeX[12]Markdown, HTML, JSON, chunks[13]Spatial JSON, Markdown, Schema-shaped JSON with citations, Ranked labels with independent 0-1 scores, Split page ranges and ZIP files[14]
OCR for scansYes[15]Yes[16]Yes[8]Yes[4]Yes[5]Yes: structure, understand, and agentic; text has no OCR; 100+ languages[17]
HandwritingYes[18]Yes[19]Yes[8]Not published[4]Not published[20]Yes: printed-style in understand; cursive/freeform needs agentic[21]
TablesYes[1]Yes[19]Yes[8]Yes[22]Yes[5]Yes: spans and bounds; complex tables may need agentic mode[21]
Layout and bounding boxesYes[23]Yes[19]Yes[24]Yes[25]Yes[26]Yes: element and optional word bounds; word bounds exclude XLSX[21]
Per-field confidenceYes[27]Yes[28]Yes[29]No[30]Yes[31]Yes: 0-1 relative signal, not a probability[32]
Source citations and groundingYes[27]Yes[28]Yes[33]Yes[25]Yes[26]Yes: field boxes, match labels, confidence, and source boxes[32]
Schema extractionYes[34]Yes[35]Yes[36]Not published[4]Yes[26]Yes: closed JSON Schema subset; 128 KB, 2,000 nodes, depth 5[37]
Free tierIncludes 10K credits (Free plan, $0/month)[1]$150 in free usage (Standard plan)[7]10,000 free credits, then pay-as-you-go (no contract, monthly minimum or sales call)[8]Free and open source (MIT)[4]Free plan: $20/month usage allowance on a work email, $10 on a personal email[26]5,000 credits/month; no card; all parse modes, including Auto[38]
Pricing modelCredits per page by tier; 1,000 credits = $1.25 (i.e. $0.00125/credit). Parse v2 tiers: Fast 1, Cost-effective 3, Agentic 10, Agentic Plus 45 credits/page. Add-ons: layout extraction +3, enriched forms +10 per form page, spreadsheet 1/sheet, audio 3/min.[39]USD per 1,000 pages, per endpoint; Growth/Enterprise custom with volume discounts[40]Credits per page by operation and mode (Performance vs Light); plan sets the per-credit rate[41]free OSS; you pay only for your own compute[4]Per 1,000 pages per processor (usage draws down monthly included allowance); open-source Marker is free to self-run[26]Credits/page by endpoint and mode; Auto routes each page and bills that mode's rate; subscription plus capped overage[42]
DeploymentSaaS (US and EU regions), VPC / hybrid cloud, single-tenant SaaS, BYOC (Azure, AWS, GCP), self-hosting[43]SaaS, VPC, on-prem, air-gapped[2]SaaS, VPC[3]open source, local, on-prem / air-gapped, self-hosted API server (docling-serve), MCP server[4]SaaS (US, EU +25%), VPC (Enterprise), air-gapped on-prem (Enterprise), open source, local[26]Hosted API: Nutrient-managed cloud, Self-hosted: Data Extraction SDK for Python and Java, no network required; OCR and ICR run on your infrastructure with zero external API calls, Local VLM: Ollama, LM Studio, or vLLM on your own hardware, or your own OpenAI or Anthropic key, Desktop: Extract Studio for Apple silicon Macs (macOS Tahoe 26.4+); the engine runs on the Mac and, with a local model, documents never leave it; Nutrient counts pages for credits, .NET data extraction SDK also offered[44]
SDKsPython (llama-cloud, PyPI 2.18.0 at fetch), TypeScript (@llamaindex/llama-cloud), Go, Java, CLI, REST API, n8n node[45]Python, Node.js, Go, REST API, CLI[46]Python, TypeScript, Java, Go, CLI[47]Python (pip install docling; PyPI 2.139.0 at fetch, Python >=3.10), CLI, REST via docling-serve[48]Python (pip install datalab-python-sdk), CLI, REST API[49]REST API, Python SDK, Java SDK, .NET page referenced, curl, JavaScript, and raw HTTP samples[50]
MCP or agent toolsHosted LlamaParse Platform MCP at mcp.llamaindex.ai/mcp (Parse, Classify, Extract, Split, Index); docs-search MCP; agent skills/plugins for Claude Code and Codex[51]MCP server (local: uvx mcp-server-reducto; hosted: https://mcp.reducto.ai/mcp), CLI, llms.txt and agent guide[52]Hosted MCP server (https://mcp.extend.ai/mcp, OAuth), extend CLI with 'extend-cli' skill, agents.md[53]docling-mcp server (uvx docling-mcp-server); agent skills page in docs[54]Not published[55]Hosted MCP, Data Extraction Studio, and agent skills[56]
Maximum file size or pages{"Batches": "10,000 files per batch (Pro/Enterprise)", "Classify": "512 MB", "Extract": "100 MB, 500 pages per job", "Parse": "512 MB, no page cap", "Split": "512 MB (PDF/DOCX/PPTX)"}[57]100 MB direct upload; up to 5 GB via presigned URL; no page limits on Standard plan[58]Not published[8]Not published[59]200 MB per file; 7,000 pages per request[60]Direct upload: 150 MB, URL input: 50 MB, URL timeout: 30 seconds, Processing: 5 minutes; HTTP 408 if exceeded, Page limit: not published, Test-key limits: lower, unpublished; Support-enabled[61]
ComplianceSOC 2 Type II, GDPR, HIPAA (BAA for Enterprise)[43]SOC 2 Type II (all tiers), HIPAA with signed BAA (Growth and Enterprise), Zero Data Retention (Growth and Enterprise)[62]SOC 2 Type II (stated as controls aligned with SOC 2 Type II requirements; report via Trust Center), HIPAA with BAA (add-on on Scale, included on Enterprise, not on PAYG), GDPR (eu1 region, Frankfurt)[63]Not published[4]SOC 2 Type II, BAA / DPA (Team and Enterprise), zero data retention by default (managed platform, per README), EU data residency[26]SOC 2: Type 2, audited annually, BAA: no public statement, Transport: HTTPS/TLS only, No-retention plans: files discarded after processing, Retention plans: runs stored; may train/evaluate models, Payments: Paddle[64]
Public benchmarksParseBench public leaderboard (15 Oct 2026 snapshot) LlamaParse Agentic Plus 90.2 (#1), LlamaParse Agentic 87.0 (#2), LlamaParse Cost Effective 80.6 (#5) of 149 entries (overall 0 to 100), parsebench.ai (LlamaIndex), 2026-10-15 (source)
ParseBench (LlamaIndex, ~2,000 pages, 167K rules) LlamaParse Agentic 84.9% overall at ~1.2 cents/page; Cost Effective <0.4 cents/page; formatting 85.2% (Docling 1.0%) (overall of 5 dimensions), LlamaIndex (vendor-authored; self-benchmark), 2026-04-13 (source)
OmniParseBench LlamaParse headline 90.4 (text 88.2, tables 92.6, layout 90.4) (mean of text/tables/layout family pass rates), Datalab (competitor-authored), 2026-10-08 (source)
OmniExtractBench llamaextract agentic_plus accuracy 84.93, precision 86.57, recall 93.13, coverage 616/620 (accuracy), Datalab (competitor-authored), 2026-09-16 (source)[65]		Parse r-1 vs Reducto's previous agentic pipeline 20% reduction in error rate (error rate (preview)), vendor (Reducto), 2026-09-01 (source)
Extraction benchmark commissioned by Reducto, run by micro1 (225 documents) Reducto Deep Extract: 100% coverage, 99.6% precision, 99.6% recall, 99.3% leaf accuracy; Extend MAX: 93.3% coverage, 86.4% precision, 92.7% recall, 92.8% leaf accuracy (coverage / precision / recall / leaf accuracy), vendor-commissioned (Reducto; conducted by micro1), 2026-09-17 (source)
RD-TableBench (1,000 complex table images) Not published (hierarchical Needleman-Wunsch table similarity), vendor (Reducto), 2024-11-04 (source)
RealDoc-Bench, Reducto rows (run by Extend) layout adjusted F1 0.759; Document Q&A 91.1% (Reducto Agentic) (adjusted F1 / Q&A accuracy), competitor (Extend), 2026-05-26 (source)
Unstructured parsing benchmark, Reducto Agentic row (run by Unstructured) (page shows '2026 (no day shown)'; date here is the fetch date) adjusted CCT 0.812; table cell content accuracy 0.708; element alignment 0.595 (see source), competitor (Unstructured), 2026-10-15 (source)[68]		RealDoc-Bench (1,500 layout samples; 1,359 Q&A prompts, 581 documents) Extend Parse 2.0: Q&A accuracy 95.7%, layout adjusted F1 0.847; Reducto layout F1 0.759, Reducto Agentic Q&A 91.1% (adjusted F1 / Q&A accuracy), vendor (Extend), 2026-05-26 (source)
LongArray-Extract (45 PDFs) 99.2% mean per-document accuracy; 45 of 45 completed (mean accuracy, failed runs scored zero), vendor (Extend), 2026-06-02 (source)
PoliTax Split (page shows '2026 (no day captured)'; date here is the fetch date) best harness F1 72.48% (Claude Opus 4.6); '+28.4 pts' largest F1 lift on homepage (split F1), vendor (Extend), 2026-10-15 (source)
Reducto-commissioned micro1 extraction benchmark, Extend MAX row 93.3% coverage, 86.4% precision, 92.7% recall, 92.8% leaf accuracy (see source), competitor-commissioned (Reducto), 2026-09-17 (source)[73]		Granite-Docling-258M model card, FinTabNet 150dpi TEDS structure 0.97, TEDS with content 0.96 (smoldocling-256m-preview 0.82 / 0.76) (TEDS), IBM (model card; this is the Granite-Docling VLM, not the default Docling PDF pipeline), 2025-09-17 (source)
Granite-Docling layout (same card) mAP 0.27, F1 0.86, precision 0.92, recall 0.88 (layout), IBM, 2025-09-17 (source)
Granite-Docling full-page OCR (same card) edit distance 0.45 (lower better), F1 0.84 (OCR), IBM, 2025-09-17 (source)
olmOCR-bench (Datalab run) docling (GPU) 50.3 overall, 64.0 digital-only, 2.1 pg/s (olmocr-bench macro average), Datalab (competitor-authored), 2026-07-20 (source)
ParseBench Docling semantic formatting 1.0% (formatting dimension), LlamaIndex (competitor-authored), 2026-04-13 (source)[74]		olmOCR-bench (Datalab README table) Marker balanced 76.0 overall / 83.5 digital-only; fast 66.6; fast no-OCR 43.6 (macro-average of 8 categories), Datalab, 2026-07-20 (source)
OmniParseBench Datalab accurate 92.7 headline, balanced 91.6 (mean of text/tables/layout), Datalab, 2026-10-08 (source)
OmniExtractBench datalab-accurate accuracy 93.85, balanced 93.48 (accuracy), Datalab, 2026-09-16 (source)[5]		ParseBench public row 76.4; paired nightly: 82.8 (overall 0 to 100), LlamaIndex, 2026-10-15 (source)
ParseBench nightly 82.8; paired public row: 76.4 (overall 0 to 100), Nutrient, 2026-10-15 (source)
opendataloader-bench, Nutrient's own run understand 0.933; agentic 0.930; structure 0.892; text 0.889 (overall 0 to 1), Nutrient, 2026-10-16 (source)
opendataloader.org leaderboard Nutrient row (free CLI) 0.885; opendataloader hybrid 0.907 (overall 0 to 1), opendataloader.org, 2026-09-23 (source)[75]

How to read this list

Every vendor below is a direct substitute for LlamaParse on at least one job: parsing to Markdown or JSON, schema extraction, classification, or splitting. Facts come from each vendor's own pricing and documentation pages on the fetched date, with sources listed below. Benchmark numbers are labeled with who ran them; none is independent of a vendor on this page.

Open source and free local options

Docling is MIT-licensed with local execution, docling-serve, and an MCP server. Marker's code is Apache-2.0 but its model weights require a commercial license above $5 million in funding or revenue ($2 million for Chandra). Unstructured's library is Apache-2.0 but its own docs call it not production-ready. Nutrient's PDF-to-Markdown CLI is free for standard conversion but carries a proprietary license.

Pricing at a glance

LlamaParse: $0.00125 to $0.056 per page by tier (our arithmetic from $1.25 per 1,000 credits). Reducto: $10 per 1,000 pages Parse r-1. Extend: 2 credits per Performance parse page at $0.0125 per credit on pay-as-you-go. Datalab: per 1,000 pages per processor with a $20 monthly free allowance on a work email. Docling: free. Nutrient: 1 to 18 credits per parse page, 5,000 free credits a month.

Benchmarks, with who ran them

Nutrient's published benchmark results, as recorded on 16 October 2026: on LlamaIndex's ParseBench the public leaderboard row for Nutrient agentic is 76.4. Nutrient's own nightly run of 15 October 2026 scores 82.8 on the same test and is not on parsebench.ai yet; in that nightly run, understand mode scores 64.0. LlamaParse Agentic Plus leads the public leaderboard at 90.2. Nutrient is not on Datalab's OmniParseBench or OmniExtractBench public leaderboards. In Nutrient's own run on the opendataloader-bench corpus the API scores 0.933 in understand mode and 0.930 in agentic; on the public opendataloader.org leaderboard Nutrient's row (the free CLI) scores 0.885, behind opendataloader hybrid at 0.907.

LlamaIndex's ParseBench leaderboard scores LlamaParse Agentic Plus 90.2 and LlamaParse Agentic 87.0. Datalab's OmniParseBench scores Datalab accurate 92.7, Reducto 90.8, LlamaParse 90.4, Extend 83.3. Datalab's olmOCR-bench run scores Marker balanced 76.0 and Docling 50.3. Nutrient's ParseBench results are 76.4 on the public row and 82.8 in its own nightly run; its opendataloader-bench run scores its API 0.933 and Docling 2.110.0 (current release 2.139.0) at 0.93 on tables, while the public opendataloader.org leaderboard puts Nutrient's free CLI at 0.885 behind opendataloader hybrid 0.907. All vendor-run.

Where Nutrient differs

The other products on this page are parsers or extraction APIs. Nutrient's Data Extraction API is the same kind of product, built by a company that has shipped document SDKs to enterprises since 2011. The facts below come from Nutrient's own public pages.

  • Founded as PSPDFKit in 2011, and the SDKs developers knew as PSPDFKit continue as Nutrient SDKs. Thousands of organizations in 80-plus countries, including Fortune 500s and governments, use them (about page).
  • 3,000-plus organizations and 15 percent of Global 500 companies rely on Nutrient, with over a billion document interactions a year (nutrient.io).
  • One engine, four deployments: hosted API in Nutrient's cloud; the Python and Java Data Extraction SDKs, self-hosted with no network required and no external API calls for OCR and ICR, with a local VLM through Ollama, LM Studio, or vLLM (Python SDK); Extract Studio on Apple silicon, where documents never leave the Mac when the model runs locally (Extract Studio); and the wider platform in the browser with WebAssembly, on your own servers with Document Engine, or air-gapped (nutrient.io).
  • Extraction is one credit pool with parse, classify, and split, and every extracted field carries a bounding box and a match label, so a reviewer can check the source instead of trusting the model. SOC 2 Type 2 audited.

What to test before switching

  • Run the same 20 documents through each API: five clean born-digital PDFs, five scans, five with tables that span pages, five with the fields your downstream system needs. Score reading order, table cells, and the fields you will actually consume.
  • Count the per-page cost at the mode or tier that passed your sample, not the cheapest tier on the pricing page. Every vendor here prices accuracy upward.
  • Check what the API returns when it is unsure: a confidence number, a bounding box, a not_found label, or nothing. That decides whether you can build a review queue.
  • Confirm retention and deployment in writing for the plan you will buy. Free and pay-as-you-go tiers often exclude BAAs, zero-retention, and private deployment.

Frequently asked questions

What is the best open source alternative to LlamaParse?

Docling, for a permissive MIT license and local execution. Marker is strong on Datalab's published benchmarks but its model weights need a commercial license above $5 million in funding or revenue.

Which alternative is cheapest for born-digital PDFs?

Docling is free. Among hosted APIs, Nutrient's text mode is 1 credit per page ($1.20 to $2.80 per 1,000 pages at its pay-as-you-go rates, our arithmetic), LlamaParse Fast is about $1.25 per 1,000 pages but returns spatial text without Markdown, and Reducto is $10 per 1,000 pages at list. Price the tier that passes your sample.

Which alternative returns citations for extracted fields?

Reducto, Extend, LlamaParse, and Nutrient return per-field citations with bounding boxes; Nutrient also returns a match label and marks fields it could not find. Datalab's extraction adds per-field citations on its fast and higher processors. Docling returns item provenance, not field citations.

Is there a LlamaParse alternative with a renewing free tier?

Nutrient's free plan renews 5,000 credits a month with no card. Datalab's free plan carries a monthly allowance. Reducto's pricing page says standard rates apply after the first $150 of free usage; Extend's 10,000 credits and Unstructured's 10,000 pages are one-time.

Sources

  1. https://www.llamaindex.ai/pricing — fetched
  2. https://docs.reducto.ai/onprem/enterprise_deployment_options.md — fetched
  3. https://docs.extend.ai/security/deployment-options.md — fetched
  4. https://raw.githubusercontent.com/docling-project/docling/main/README.md — fetched
  5. https://github.com/datalab-to/marker — fetched
  6. https://www.nutrient.io/guides/dws-data-extraction/api-overview/ — fetched
  7. https://reducto.ai/pricing — fetched
  8. https://www.extend.ai/pricing — fetched
  9. https://www.nutrient.io/legal/ — fetched
  10. https://docs.reducto.ai/reference/faq.md — fetched
  11. https://docs.extend.ai/parsing/configuration.md — fetched
  12. https://docling-project.github.io/docling/usage/supported_formats/ — fetched
  13. https://raw.githubusercontent.com/datalab-to/marker/master/README.md — fetched
  14. https://www.nutrient.io/guides/dws-data-extraction/parsing/ — fetched
  15. https://developers.llamaindex.ai/llamaparse/parse/features/ocr-and-languages/index.md — fetched
  16. https://reducto.ai/ — fetched
  17. https://www.nutrient.io/guides/dws-data-extraction/parsing/processing-modes/ — fetched
  18. https://developers.llamaindex.ai/llamaparse/parse/ — fetched
  19. https://docs.reducto.ai/parse/overview.md — fetched
  20. https://www.datalab.to/blog/omni-parse-bench — fetched
  21. https://www.nutrient.io/guides/dws-data-extraction/parsing/extract-document-elements/ — fetched
  22. https://arxiv.org/abs/2408.09869 — fetched
  23. https://developers.llamaindex.ai/llamaparse/parse/features/layout-and-bounding-boxes/index.md — fetched
  24. https://docs.extend.ai/parsing/overview.md — fetched
  25. https://docling-project.github.io/docling/concepts/docling_document/ — fetched
  26. https://www.datalab.to/pricing — fetched
  27. https://developers.llamaindex.ai/llamaparse/extract/guides/response-format/index.md — fetched
  28. https://docs.reducto.ai/configs/extract/citations.md — fetched
  29. https://docs.extend.ai/extraction/confidence-scores.md — fetched
  30. https://docling-project.github.io/docling/concepts/confidence_scores/ — fetched
  31. https://documentation.datalab.to/docs/recipes/structured-extraction/confidence-scoring.md — fetched
  32. https://www.nutrient.io/guides/dws-data-extraction/extract/citations-and-confidence/ — fetched
  33. https://docs.extend.ai/extraction/response-format.md — fetched
  34. https://developers.llamaindex.ai/llamaparse/extract/ — fetched
  35. https://docs.reducto.ai/extract/overview.md — fetched
  36. https://docs.extend.ai/extraction/schema.md — fetched
  37. https://www.nutrient.io/guides/dws-data-extraction/extract/define-a-schema/ — fetched
  38. https://www.nutrient.io/api/pricing/data-extraction-api/ — fetched
  39. https://developers.llamaindex.ai/llamaparse/general/pricing/ — fetched
  40. https://docs.reducto.ai/reference/credit-usage.md — fetched
  41. https://docs.extend.ai/general/how-credits-work.md — fetched
  42. https://www.nutrient.io/guides/dws-data-extraction/pricing/ — fetched
  43. https://developers.llamaindex.ai/llamaparse/general/enterprise-readiness/ — fetched
  44. https://www.nutrient.io/sdk/python/pdf-data-extraction/ — fetched
  45. https://developers.llamaindex.ai/llamaparse/parse/guides/tiers/index.md — fetched
  46. https://docs.reducto.ai/agent-guide.md — fetched
  47. https://docs.extend.ai/sdks.md — fetched
  48. https://pypi.org/pypi/docling/json — fetched
  49. https://documentation.datalab.to/docs/welcome/sdk.md — fetched
  50. https://www.nutrient.io/guides/dws-data-extraction/getting-started/ — fetched
  51. https://developers.llamaindex.ai/for-agents/index.md — fetched
  52. https://docs.reducto.ai/mcp-server.md — fetched
  53. https://docs.extend.ai/mcp.md — fetched
  54. https://docling-project.github.io/docling/usage/mcp/ — fetched
  55. https://documentation.datalab.to/llms.txt — fetched
  56. https://www.nutrient.io/api/mcp-server-pdf-automation-llm/ — fetched
  57. https://developers.llamaindex.ai/llamaparse/general/limitations/ — fetched
  58. https://docs.reducto.ai/upload/large-files.md — fetched
  59. https://docling-project.github.io/docling/usage/ — fetched
  60. https://documentation.datalab.to/docs/common/limits.md — fetched
  61. https://www.nutrient.io/guides/dws-data-extraction/file-types/ — fetched
  62. https://docs.reducto.ai/enterprise/enterprise-readiness.md — fetched
  63. https://docs.extend.ai/security/compliance.md — fetched
  64. https://www.nutrient.io/guides/dws-data-extraction/security/ — fetched
  65. https://www.llamaindex.ai/blog/parsebench — fetched
  66. https://parsebench.ai/ — fetched
  67. https://www.datalab.to/blog/omni-extract-bench — fetched
  68. https://reducto.ai/compare/reducto-vs-extend — fetched
  69. https://reducto.ai/blog/parse-r-1-model — fetched
  70. https://reducto.ai/blog/rd-tablebench — fetched
  71. https://www.extend.ai/resources/realdocbench — fetched
  72. https://unstructured.io/benchmarks — fetched
  73. https://www.extend.ai/benchmarks — fetched
  74. https://huggingface.co/ibm-granite/granite-docling-258M — fetched
  75. https://www.nutrient.io/api/data-extraction-api/benchmarks/ — fetched
  76. https://opendataloader.org/docs/benchmark — fetched

Related