Intelligent document processing
Asked as “intelligent document processing platform”, and as “IDP software”, on behalf of a mid-market B2B company. 52 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each. Added to the November 2026 Edition.
Standing · first-choice share
31%
Contested · Rossum 15%
31Nanonets15Rossum10Docsumo44others
31% of first choices, contested.
Since October 2026▼−1Since October 2026: 32% → 31%, −1 point. Inside the 11-point floor: within noise.Nanonets held the lead, −1 point on 32%, inside the 11-point floor.
By buyer segment
The same question asked on behalf of a different buyer. Each standing is computed within its segment; they sit side by side and are never added together.
Small business
Nanonets42%Clear leader↗new leaderNew leader since October 2026: Nanonets (42%) replaces Docsumo (22% then, 29% now), 13 points clear, past the 11-point floor.Standing →Mid-marketNanonets31%Contested▼−1Since October 2026: 32% → 31%, −1 point. Inside the 11-point floor: within noise.This pageEnterprise
ABBYY Vantage38%Contested▼−5Since October 2026: 43% → 38%, −5 points. Inside the 11-point floor: within noise.Standing →
Nanonets42%Clear leader↗new leaderNew leader since October 2026: Nanonets (42%) replaces Docsumo (22% then, 29% now), 13 points clear, past the 11-point floor.Standing →Mid-marketNanonets31%Contested▼−1Since October 2026: 32% → 31%, −1 point. Inside the 11-point floor: within noise.This pageEnterpriseABBYY Vantage38%Contested▼−5Since October 2026: 43% → 38%, −5 points. Inside the 11-point floor: within noise.Standing →The standing
Share is the count of first choices across the direct, paraphrase, budget and scale prompts, over all fourteen models, for a mid-market B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrantSince October 2026
01Nanonets31%0%42endorsed leader▼−1Since October 2026: 32% → 31%, −1 point. Inside the 11-point floor: within noise.32% → 31%
Nanonets31%0%42endorsed leader▼−1Since October 2026: 32% → 31%, −1 point. Inside the 11-point floor: within noise.32% → 31%02
Rossum15%12%49accepted challenger▼−1Since October 2026: 16% → 15%, −1 point. Inside the 11-point floor: within noise.16% → 15%
Rossum15%12%49accepted challenger▼−1Since October 2026: 16% → 15%, −1 point. Inside the 11-point floor: within noise.16% → 15%03
Docsumo10%0%25accepted challenger▲+4Since October 2026: 6% → 10%, +4 points. Inside the 11-point floor: within noise.6% → 10%
Docsumo10%0%25accepted challenger▲+4Since October 2026: 6% → 10%, +4 points. Inside the 11-point floor: within noise.6% → 10%04
Parseur8%10%10accepted challenger=heldSince October 2026: 8% → 8%, ±0 points. Inside the 11-point floor: within noise.8% → 8%
Parseur8%10%10accepted challenger=heldSince October 2026: 8% → 8%, ±0 points. Inside the 11-point floor: within noise.8% → 8%05ABBYY Vantage6%28%50criticized challenger▲+2Since October 2026: 4% → 6%, +2 points. Inside the 11-point floor: within noise.4% → 6%
ABBYY Vantage6%28%50criticized challenger▲+2Since October 2026: 4% → 6%, +2 points. Inside the 11-point floor: within noise.4% → 6%06
UiPath Document Understanding4%16%44accepted challenger=heldSince October 2026: 4% → 4%, ±0 points. Inside the 11-point floor: within noise.4% → 4%
UiPath Document Understanding4%16%44accepted challenger=heldSince October 2026: 4% → 4%, ±0 points. Inside the 11-point floor: within noise.4% → 4%07Google Document AI Lab in the set4%24%29accepted challenger▼−2Since October 2026: 6% → 4%, −2 points. Inside the 11-point floor: within noise.6% → 4%
08Amazon Textract4%30%27criticized challenger=heldSince October 2026: 4% → 4%, ±0 points. Inside the 11-point floor: within noise.4% → 4%
09Azure AI Document Intelligence4%33%18criticized challenger▲+4Since October 2026: 0% → 4%, +4 points. Inside the 11-point floor: within noise.0% → 4%
10Microsoft Azure AI Document Intelligence2%0%15accepted challenger=heldSince October 2026: 2% → 2%, ±0 points. Inside the 11-point floor: within noise.2% → 2%
11
Tungsten Automation2%18%11accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise.0% → 2%
Tungsten Automation2%18%11accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise.0% → 2%Show the two products at 0%, ordered by negative rate
12
Hyperscience Hypercell0%24%33accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
Hyperscience Hypercell0%24%33accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%13
Automation Anywhere0%14%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
Automation Anywhere0%14%14accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%The floor is 11 points of share, measured: how far the models move a leader on their own when the same questions are asked twice with nothing changed. A larger change is movement; a smaller one can't be told apart from repeat variation, and both are shown. Each index measures its own floor from its own repeat, over its own categories, so the floor differs from one index to the next. Both editions asked the same fourteen models. How the floor is measured
Bars are the share of first choices, 0 to 100Every product with at least 10 labels here. Every product name links to its product page.
Google Document AI is made by Google, whose model Gemini 3.5 Flash is in the set. On the four share prompts that model made it the first choice zero times of 4; the other thirteen models two times of 52. Lab treatment is defined on the method page; the row is marked, not excluded.
For buyers
All twenty-eight head-to-head pages: the top eight products, each against each
Nanonets vs ABBYY VantageNanonets vs UiPath Document UnderstandingNanonets vs Google Document AINanonets vs Amazon TextractRossum vs DocsumoRossum vs ParseurRossum vs ABBYY VantageRossum vs UiPath Document UnderstandingRossum vs Google Document AIRossum vs Amazon TextractDocsumo vs ParseurDocsumo vs ABBYY VantageDocsumo vs UiPath Document UnderstandingDocsumo vs Google Document AIDocsumo vs Amazon TextractParseur vs ABBYY VantageParseur vs UiPath Document UnderstandingParseur vs Google Document AIParseur vs Amazon TextractABBYY Vantage vs UiPath Document UnderstandingABBYY Vantage vs Google Document AIABBYY Vantage vs Amazon TextractUiPath Document Understanding vs Google Document AIUiPath Document Understanding vs Amazon TextractGoogle Document AI vs Amazon Textract
Recommended versus criticized
Every product with at least 10 labels here, on both axes. The 30% line names a quadrant, not the verdict above: that one needs more than 40%.
Criticized challengerCriticized default
Negative label rate →
010203040506G07
A08
A09
M10
111213Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative50%
Key
01Nanonets31%
Nanonets31%02Rossum15%
Rossum15%03Docsumo10%
Docsumo10%04Parseur8%
Parseur8%05ABBYY Vantage6%
ABBYY Vantage6%06UiPath Document Understanding4%
UiPath Document Understanding4%07Google Document AI4%
08Amazon Textract4%
09Azure AI Document Intelligence4%
10Microsoft Azure AI Document Intelligence2%
11Tungsten Automation2%
Tungsten Automation2%12Hyperscience Hypercell0%
Hyperscience Hypercell0%13Automation Anywhere0%
Automation Anywhere0%What they warned about
Zero of fourteen models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Gemini 3.5 Flash, Perplexity Sonar, Grok 4.20, Mistral Small, DeepSeek V4 Flash, Llama 4 Maverick, Qwen 3.7 Flash, Kimi K2, GLM 4.7 FlashX, MiniMax M2.5, GPT-6 Luna and Muse Glimmer 30B changed. A high negative share on a product with few labels is a warning. A low share on a product with many labels is salience, not sentiment.
ABBYY Vantage28%
14 of 50 labels negative · 9 of 14 models · 4 hard negative
“What to avoid if you're on a tight budget - ABBYY, Hyperscience, Rossum, UiPath: These are enterprise-grade but quote-only” DeepSeek V4 Flash, budget prompt
Rossum12%
6 of 49 labels negative · 6 of 14 models · 4 hard negative
“Avoid If Budget Is Tight | Rossum | $18,000/year | Enterprise-focused, annual contracts” Kimi K2, budget prompt
UiPath Document Understanding16%
7 of 44 labels negative · 6 of 14 models · 4 hard negative
“Avoid enterprise tools like ABBYY Vantage, UiPath, Rossum, or Hyperscience” Grok 4.20, budget prompt
Hyperscience Hypercell24%
8 of 33 labels negative · 6 of 14 models · 3 hard negative
“Avoid starting with Rossum, ABBYY, Hyperscience, or similar enterprise platforms” Perplexity Sonar, budget prompt
What they cite
Fourteen of the fourteen models returned a source list in this edition: five return the pages they cited and nine the search results they consulted.
Sites the answers cite
73 of 84 answers in this category came back with a source list, from 14 of 14 models: citations where the model returns them, or the search results it consulted. 887 links across 234 sites, every framing counted. Ranked by the number of answers carrying the site or page. 34 of the 252 answers across every segment cited this index's own page for the category; the method page measures whether that reading tilts an answer.
vendor site · G231 answers · 52 citations · 10 models
vendor site · Nanonets28 answers · 33 citations · 11 models
vendor site · Docsumo27 answers · 53 citations · 10 models
23 answers · 37 citations · 8 models
22 answers · 22 citations · 9 models
17 answers · 22 citations · 8 models
vendor site · Parseur16 answers · 28 citations · 7 models
14 answers · 15 citations · 8 models
vendor site · Guideflow13 answers · 13 citations · 5 models
13 answers · 13 citations · 8 models
vendor site · Cycloid12 answers · 16 citations · 7 models
12 answers · 12 citations · 10 models
Pages the answers cite
The ten pages named in the most answers, by full address. A page here is one the models returned with a recommendation, not one the index endorses.
23 answers · 8 models
22 answers · 9 models
21 answers · 9 models
18 answers · 9 models
14 answers · 7 models
13 answers · 7 models
13 answers · 5 models
13 answers · 8 models
12 answers · 10 models
11 answers · 6 models
Search against answers
Each company's standing in the answers beside its site's footprint in Google search, one row a site: the products the models named on it with their shares, and the share they add up to; monthly searches on Google, and DataForSEO's estimate of AI search demand (modeled from search signals, directional, not a count of queries to any assistant), for the most-searched of the company's and its products' names (the name is in each row's hover text); estimated monthly organic visits to the site; and its best position in Google's top ten for “intelligent document processing platform”, “intelligent document processing platforms”. US estimates from DataForSEO and Google's Ads Transparency Center. A small company's site, or a mid-sized company's site for its flagship, is marked company; a product on a large parent's site (Google, Microsoft) has no site figures. A column with no figures for this category is left out, and an empty cell means none were seen, not none exist. Two measurements side by side: neither is read as the cause of the other.
| Company and products | Share | Own site cited | Name searches, Google | AI search demand, est. | Organic visits | Paid search a month, est. | Google ads, last 30 days |
|---|---|---|---|---|---|---|---|
| Nanonets nanonets.com | 31% | 103 | 1,900 | 29 | 7,984 | 2 | |
| Rossum rossum.ai | 15% | 125 | 1,600 | 2,838 | 3,120 | 24 | |
| Docsumo docsumo.com | 10% | 73 | 590 | 3 | 12,362 | 0 | |
| Parseur parseur.com | 8% | 42 | 880 | 9 | 17,087 | ||
| ABBYY Vantage abbyy.com | 6% | 136 | 210 | 1 | 36,786 | 14 | |
| Microsoft parent site Microsoft Entra ID 4%, Microsoft Azure AI Document Intelligence 2% | 6% | 499 | 2,240,000 | 403,136 | |||
| UiPath Document Understanding uipath.com | 4% | 120 | 260 | 6 | 161,995 | $74 | 107 |
| Google Cloud parent site Google Document AI 4% | 4% | 83 | 165,000 | 7,596 | |||
| Amazon parent site Amazon Textract 4% | 4% | 79 | 151,000,000 | 1,380,939 | |||
| Azure azure.com Azure AI Document Intelligence 4% | 4% | 54 | 301,000 | 47,904 |
Google's top ten for the two searches hold 17 sites; 1 of them are among the sites the models cited here (g2.com). The first result for “intelligent document processing platform” is extend.ai.
How they answered
Six framings of the same buying question, each sent to every model in a fresh session with search on. One row per model, so a row shows whether it held its answer under rewording, what it named when cost was the constraint, and what it argued against. Computed from the raw judge labels.ShowHide
How they answered
Six framings of the same buying question, each sent to every model in a fresh session with search on. One row per model, so a row shows whether it held its answer under rewording, what it named when cost was the constraint, and what it argued against. Computed from the raw judge labels.
ShowHideModelDirect“What is the best intelligent document processing platform for a mid-market B2B company?”Paraphrase“Which IDP software would you recommend to a mid-sized B2B company?”Comparative“What are the top intelligent document processing platforms and how do they differ?”Budget-constrained“What is the best intelligent document processing platform for a company with a limited budget?”Scale-constrained“We are a 500 person company evaluating an intelligent document processing platform. What should we look at?”Negative“Which intelligent document processing platforms should I avoid or be cautious about?”
Claude Haiku 4.5NanonetsDocsumoChangedno first choiceDocsumo, Lidono first choiceagainst: ABBYY Vantage, UiPath Document Understanding
Two alternatives
Doxis AI.dp, RossumThree alternatives
Azure AI Document Intelligence, Nanonets, RossumSix alternatives
Amazon Textract, Azure AI Document Intelligence, Google Document AI, Mistral OCR, Zenphi, super.AI DocumentGPT-5.4 miniABBYY VantageWorkOSChangedABBYY Vantage, Hyperscience Hypercell, RossumAmazon Textractno first choiceagainst: Docparser
Three alternatives
AWS IDP, Azure AI Document Intelligence, RossumTwo alternatives
Auth0, Microsoft Entra External IDFive alternatives
AWS, Google Cloud, Microsoft, Tungsten Automation, UiPath Document UnderstandingThree alternatives
Azure AI Document Intelligence, DocuPipe, Google Document AIGemini 3.5 FlashNanonetsagainst: Amazon Textract, Azure AI Document Intelligence, Google Document AI, IBM DatacapRossumChangedagainst: Backstageno first choiceMicrosoft Azure AI Document Intelligenceagainst: ABBYY Vantage, Hyperscience Hypercell, Kofaxno first choiceagainst: ABBYY FlexiCapture, Amazon Textract, Azure AI Document Intelligence, Google Document AI, Kofax, Tungsten Automation
Three alternatives
ABBYY Vantage, Docsumo, RossumNine alternatives
ABBYY Vantage, Amazon Textract, Auth0, Google Document AI, JumpCloud, Microsoft Entra ID, Palo Alto Networks Cortex Cloud, Port, WorkOSTwelve alternatives
ABBYY Vantage, Amazon Textract, Automation Anywhere Document Automation, Google Document AI, Hyperscience Hypercell, Instabase, LlamaParse, Microsoft Azure AI Document Intelligence, Nanonets, Rossum, Tungsten Automation, UiPath Document UnderstandingSeven alternatives
Amazon Textract, Docsumo, Google Document AI, IBM Docling, Nanonets, Paperless-ngx, Unstructured.ioPerplexity SonarNanonetsagainst: ABBYY Vantage, GrooperParseurChangedABBYY VantageParseuragainst: ABBYY Vantage, Amazon Textract, Azure AI Document Intelligence, Hyperscience Hypercell, Rossumno first choiceagainst: Amazon Textract, Azure AI Document Intelligence, Google Document AI
Three alternatives
Docsumo, Microsoft Azure AI Document Intelligence, ParseurTwo alternatives
ABBYY Vantage, UiPath Document UnderstandingNine alternatives
Amazon Textract, Google Document AI, Grooper, Hyperscience Hypercell, Microsoft Azure AI Document Intelligence, Nanonets, Rossum, Tungsten TotalAgility, UiPath Document UnderstandingTwo alternatives
Docparser, NanonetsGrok 4.20RossumNanonetsChangedABBYY Vantageagainst: Microsoft AI BuilderNanonetsagainst: ABBYY Vantage, Hyperscience Hypercell, Rossum, UiPath Document Understandingno first choiceagainst: ABBYY Vantage, AWS, Adobe, Altilia, AntWorks, Automation Anywhere, Datamatics, FormX AI, Google Document AI, Hyperscience Hypercell, Microsoft, Mindee, UiPath Document Understanding
Four alternatives
ABBYY Vantage or FlexiCapture, Docsumo, Hyperscience Hypercell, UiPath Document UnderstandingThree alternatives
ABBYY Vantage, Rossum, UiPath Document UnderstandingFive alternatives
Hyperscience Hypercell, OpenText Intelligent Capture, Rossum, Tungsten Automation, UiPath Document UnderstandingFour alternatives
Docparser, Docsumo, Microsoft Azure AI Document Intelligence, ParseurMistral SmallABBYY Vantage, RossumRossum, UiPath Document UnderstandingChangedno first choiceDocsumo, Nanonetsno first choicenothing named
Two alternatives
Apryse, TurianTwo alternatives
ABBYY Vantage, Automation AnywhereTwo alternatives
Google Document AI, ParseurDeepSeek V4 FlashDocsumoagainst: ABBYY Vantageno first choiceChangedABBYY Vantage, Hyperscience HypercellNanonetsagainst: ABBYY Vantage, Amazon Textract, Google Document AI, Hyperscience Hypercell, Rossum, Sensible, UiPath Document Understandingno first choiceagainst: Hyperscience Hypercell, Kofax TotalAgility, Lector
Two alternatives
Nanonets, RossumFive alternatives
Infrrd, Nanonets, Rossum, Tungsten Automation (formerly Kofax) TotalAgility, UiPath Document UnderstandingTwo alternatives
Docparser, ParseurLlama 4 MaverickNanonetsagainst: ABBYY Vantage, Hyperscience HypercellTungsten AutomationChangedABBYY VantageAzure AI Document Intelligence, Google Document AI, Nanonetsno first choiceagainst: Kolena
Two alternatives
Apryse PDF SDK, ParseurThree alternatives
ABBYY Vantage, Aluma, RossumFour alternatives
Docsumo, Hyperscience Hypercell, Rossum, UiPath Document UnderstandingQwen 3.7 FlashNanonetsRossumChangedABBYY VantageAmazon Textract, Google Document AIagainst: ABBYY Vantageno first choiceagainst: ABBYY Vantage, Amazon Textract, Automation Anywhere, Azure AI Document Intelligence, Docparser, Google Document AI, Kofax, Maveric, Parseur, UiPath Document Understanding
Three alternatives
Extend, Rossum, TurianThree alternatives
Azure AI Document Intelligence, Nanonets, UiPath Document UnderstandingSeven alternatives
Amazon Textract, Automation Anywhere, Google Document AI, Hyperscience Hypercell, Microsoft Azure AI Document Intelligence, Rossum, UiPath Document UnderstandingThree alternatives
Docsumo, Microsoft Azure AI Document Intelligence, NanonetsKimi K2RossumNanonets, ParseurChangedagainst: ABBYY Vantageno first choiceDocsumo, Nanonetsagainst: ABBYY Vantage, Docling, PaddleOCR, Rossum, Tesseract OCR, UiPath Document Understanding, py-idpno first choicenothing named
Three alternatives
ABBYY Vantage, Microsoft Azure AI Document Intelligence, NanonetsFour alternatives
Docsumo, Microsoft Azure AI Document Intelligence, Rossum, UiPath Document UnderstandingFour alternatives
Amazon Textract, Azure AI Document Intelligence, DocuClipper, Google Document AIGLM 4.7 FlashXUiPath Document UnderstandingABBYY VantageChangedABBYY VantageTurboDocno first choicenothing named
Four alternatives
ABBYY Vantage, Automation Anywhere Intelligent Automation, Microsoft Azure AI Document Intelligence, ServiceNow Document ManagementThree alternatives
Automation Anywhere IQ Bot, Nanonets, UiPath Document UnderstandingNine alternatives
Affinda, Automation Anywhere, DocuPipe, Hyperscience Hypercell, OpenText Core Capture, Rossum, SAP Document AI, Tungsten Automation, UiPath Document UnderstandingFour alternatives
Docsumo, Nanonets, PDF AI, ReductoMiniMax M2.5NanonetsMicrosoft Entra ID, OktaChangedno first choiceNanonetsagainst: Hyperscience Hypercell, Rossumno first choicenothing named
Five alternatives
ABBYY Vantage, Docsumo, Hyperscience Hypercell, Rossum, UiPath Document UnderstandingTwo alternatives
JumpCloud, OneLoginFour alternatives
ABBYY Vantage, Hyperscience Hypercell, ServiceNow, UiPath Document UnderstandingTwo alternatives
Azure AI Document Intelligence, DocsumoGPT-6 LunaRossumMicrosoft Entra IDChangedABBYY Vantage, Hyperscience Hypercell, Tungsten TotalAgilityagainst: Amazon TextractAzure AI Document Intelligenceno first choiceagainst: Amazon Textract, Azure AI Document Intelligence, Google Document AI
Three alternatives
ABBYY Vantage, Nanonets, UiPath Document UnderstandingOne alternative
Okta Workforce IdentityFour alternatives
Google Document AI, Microsoft Azure AI Document Intelligence, Rossum, UiPath Document UnderstandingOne alternative
NanonetsMuse Glimmer 30BNanonets, Rossumagainst: Kofax, Tungsten AutomationNanonetsChangedagainst: ABBYY Vantageno first choiceParseurno first choiceagainst: ABBYY Intelligent Document Processing / FlexiCapture, Microsoft Syntex, Rossum, Tesseract, UiPath Agentic Automation, UiPath Document Understanding
Four alternatives
ABBYY Vantage, Automation Anywhere, Google Document AI, UiPath Document UnderstandingTwo alternatives
Rossum, UiPath Document UnderstandingFour alternatives
Docling, Microsoft Azure AI Document Intelligence, Nanonets, UnstractBold is the first choiceAlternatives are counted; the count opens them.What the answer argued against
The record
One row per call: the version string exactly as returned, whether the model searched, sources cited, and latency.
Eighty-four rows: every prompt, every model, every answer.
| Prompt | Model | Version string | Time (UTC) | Searched | Sources | Latency |
|---|---|---|---|---|---|---|
| Direct recommendation | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 11:51 | yes | 10 | 8 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 16:04 | yes | 3 | 6 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 10:57 | yes | 15 | 24 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-11-01 12:09 | yes | 10 | 5 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 18:00 | yes | 15 | 18 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:14 | yes | 5 | 5 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 10:58 | yes | 23 | 24 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 19:04 | yes | 5 | 3 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 18:20 | yes | 5 | 29 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 11:37 | yes | 14 | 45 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 13:44 | yes | 14 | 36 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 19:30 | yes | 9 | 40 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:56 | yes | 4 | 18 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 11:45 | yes | 14 | 25 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 10:22 | yes | 18 | 9 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 10:52 | yes | 3 | 5 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 09:11 | no | 0 | 11 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-11-01 18:36 | yes | 10 | 3 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 14:50 | yes | 14 | 13 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 09:16 | yes | 5 | 5 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 11:39 | yes | 23 | 33 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 13:19 | yes | 5 | 2 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 10:11 | no | 0 | 34 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 15:10 | yes | 17 | 34 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 11:42 | yes | 19 | 116 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 17:16 | yes | 10 | 24 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-11-01 16:36 | yes | 2 | 8 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:37 | yes | 24 | 30 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 17:25 | yes | 9 | 7 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 08:48 | yes | 7 | 9 s |
| Comparative | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 09:45 | yes | 13 | 27 s |
| Comparative | Perplexity Sonar | sonar | 2026-11-01 12:44 | yes | 10 | 6 s |
| Comparative | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 16:38 | yes | 8 | 19 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 10:22 | yes | 7 | 10 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 17:33 | yes | 22 | 53 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 11:43 | yes | 5 | 3 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 13:21 | yes | 10 | 25 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 11:25 | yes | 14 | 65 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 17:56 | yes | 18 | 37 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 11:13 | yes | 14 | 21 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-11-01 18:29 | yes | 9 | 31 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 17:36 | yes | 23 | 46 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 10:24 | yes | 17 | 9 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 17:28 | yes | 3 | 5 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 16:02 | yes | 8 | 22 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-11-01 13:53 | yes | 10 | 4 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 18:58 | yes | 25 | 14 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:16 | yes | 5 | 5 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 18:23 | yes | 25 | 34 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 19:24 | yes | 5 | 3 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 10:07 | yes | 9 | 35 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 15:41 | yes | 25 | 65 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 14:44 | yes | 24 | 30 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 18:18 | yes | 15 | 24 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 17:05 | yes | 2 | 13 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 14:32 | yes | 25 | 27 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 16:41 | no | 0 | 6 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 14:07 | no | 0 | 7 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 16:34 | no | 0 | 17 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-11-01 09:00 | yes | 10 | 9 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 16:04 | yes | 5 | 17 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:42 | no | 0 | 5 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 12:44 | yes | 16 | 37 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 18:16 | yes | 5 | 2 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 14:28 | no | 0 | 29 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 10:27 | yes | 14 | 52 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:50 | yes | 10 | 20 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 15:20 | no | 0 | 21 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 17:31 | yes | 2 | 21 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 12:10 | yes | 14 | 29 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 19:42 | yes | 20 | 10 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 09:36 | yes | 6 | 7 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.6-flash (asked for gemini-3.5-flash; the API answered as this version) | 2026-11-01 12:19 | no | 0 | 15 s |
| Negative framing | Perplexity Sonar | sonar | 2026-11-01 18:36 | yes | 10 | 5 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 17:25 | yes | 10 | 11 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 13:52 | yes | 5 | 7 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 14:37 | yes | 25 | 41 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 12:56 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 08:42 | no | 0 | 33 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 17:22 | yes | 24 | 30 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 09:35 | yes | 15 | 26 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 18:29 | no | 0 | 20 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-11-01 08:54 | yes | 3 | 20 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 13:34 | yes | 25 | 34 s |
Normalization in this category
Every judgment call made between the raw labels and the numbers above, listed so it is visible and reversible.
ShowHide
Category-scoped readings
ABBYY read as ABBYY Vantage
ABBYY (FlexiCapture) read as ABBYY Vantage
ABBYY (Vantage) read as ABBYY Vantage
ABBYY (Vantage/FlexiCapture) read as ABBYY Vantage
AWS Textract read as Amazon Textract
Azure Form Recognizer (AI Builder) read as Azure AI Document Intelligence
Google Cloud Document AI read as Google Document AI
Hyperscience read as Hyperscience Hypercell
Hyperscience (Hypercell) read as Hyperscience Hypercell
Hyperscience (now part of Tungsten Automation) read as Hyperscience Hypercell
OpenText Capture read as OpenText Core Capture
UiPath read as UiPath Document Understanding
UiPath (Agentic Automation/IDP features) read as UiPath Document Understanding
UiPath (Document Understanding) read as UiPath Document Understanding
UiPath Document Understanding / IXP read as UiPath Document Understanding
UiPath IXP read as UiPath Document Understanding
Unresolved, counted raw
ABBYY Intelligent Document Processing / FlexiCapture
ABBYY Vantage or FlexiCapture
AWS IDP
Adobe
Altilia
Aluma
Apache Tika
Apryse (formerly PDFTron)
Apryse PDF SDK
Automation Anywhere Intelligent Automation
Datacap
DocTR
Documate/Affinda
Dokuflex
Extend
FormX AI (by Kofax/Tungsten or similar)
GdoczAI / Documind
Hyland OnBase
IBM Docling
IBM Watson Document Processing
Klearsstack
Kraftful
Lector
Maveric
Mistral OCR
Nividous
PDF AI
PaddleOCR
Paperless-ngx
Sensible
ServiceNow Document Management
Snoh Fusion
Tungsten Automation formerly Kofax
TurboDoc
Unstructured.io
py-idp
super.AI Document
Discontinued, still offered
No shut-down product was recommended here.