Intelligent document processing
Asked as “intelligent document processing platform”, and as “IDP software”, on behalf of a mid-market B2B company. 50 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each. Added to the October 2026 Edition on October 4, 2026; its answers are read by the distilled judge (ai-indexes-judge-qwen3-14b-run3), not the claude-opus-5 judge of the earlier categories: how the two compare.
Standing · first-choice share
32%
Contested · Rossum 16%
32Nanonets16Rossum08Parseur44others
32% of first choices, contested.
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.
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 September 2026
04Google Document AI Lab in the set6%13%23accepted challengernewNew since September 2026: not ranked then, 6% now.
05
UiPath Document Understanding4%24%46accepted challengernewNew since September 2026: not ranked then, 4% now.
UiPath Document Understanding4%24%46accepted challengernewNew since September 2026: not ranked then, 4% now.Show the four products at 0%, ordered by negative rate
11Azure AI Document Intelligence0%27%15criticized challengernewNew since September 2026: not ranked then, 0% now.
10
Tungsten Automation0%25%12criticized challengernewNew since September 2026: not ranked then, 0% now.
Tungsten Automation0%25%12criticized challengernewNew since September 2026: not ranked then, 0% now.09
Automation Anywhere0%18%11accepted challengernewNew since September 2026: not ranked then, 0% now.
Automation Anywhere0%18%11accepted challengernewNew since September 2026: not ranked then, 0% now.08
Hyperscience Hypercell0%17%18accepted challengernewNew since September 2026: not ranked then, 0% now.
Hyperscience Hypercell0%17%18accepted challengernewNew since September 2026: not ranked then, 0% now.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 is noise, and both are shown. Movement is read over the twelve models both editions asked; GPT-6 Luna, Muse Glimmer 30B joined this edition and are in the standing but not yet in the comparison. 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 one time 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-one head-to-head pages: the top seven products, each against each
Nanonets vs UiPath Document UnderstandingNanonets vs Amazon TextractNanonets vs ABBYY VantageRossum vs DocsumoRossum vs Google Document AIRossum vs UiPath Document UnderstandingRossum vs Amazon TextractRossum vs ABBYY VantageDocsumo vs Google Document AIDocsumo vs UiPath Document UnderstandingDocsumo vs Amazon TextractDocsumo vs ABBYY VantageGoogle Document AI vs UiPath Document UnderstandingGoogle Document AI vs Amazon TextractGoogle Document AI vs ABBYY VantageUiPath Document Understanding vs Amazon TextractUiPath Document Understanding vs ABBYY VantageAmazon Textract vs ABBYY Vantage
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 →
01
02
03G04
05A06
07080910A11
Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative50%
Key
01Nanonets32%
Nanonets32%02Rossum16%
Rossum16%03Docsumo6%
Docsumo6%04Google Document AI6%
05UiPath Document Understanding4%
UiPath Document Understanding4%06Amazon Textract4%
07ABBYY Vantage4%
ABBYY Vantage4%08Hyperscience Hypercell0%
Hyperscience Hypercell0%09Automation Anywhere0%
Automation Anywhere0%10Tungsten Automation0%
Tungsten Automation0%11Azure AI Document Intelligence0%
What they warned about
Two of fourteen models held their first choice under the paraphrase. Claude Haiku 4.5, GPT-5.4 mini, Perplexity Sonar, Grok 4.1 Fast, Mistral Small, DeepSeek V4 Flash, Llama 4 Maverick, Qwen 3.7 Flash, Kimi K2, 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.
UiPath Document Understanding24%
11 of 46 labels negative · 8 of 14 models · 3 hard negative
“**Avoid ABBYY/UiPath/Hyperscience** unless you have dedicated IT resources” Kimi K2, paraphrase prompt
ABBYY Vantage24%
9 of 38 labels negative · 6 of 14 models · 2 hard negative
“**Avoid** enterprise platforms like ABBYY, Rossum, or UiPath for now, as their annual minimums ($18k+)” Qwen 3.7 Flash, budget prompt
Amazon Textract
14%
4 of 28 labels negative · 4 of 14 models · 1 hard negative
“**Avoid** if you are non-technical: **Azure AI** and **AWS Textract**” Qwen 3.7 Flash, negative prompt
Azure AI Document Intelligence
27%
4 of 15 labels negative · 4 of 14 models · 1 hard negative
“**Avoid** if you are non-technical: **Azure AI** and **AWS Textract**” Qwen 3.7 Flash, negative prompt
What they cite
Citations exist only for the models that return a source list: fourteen of the fourteen in this edition, and all six flagship models on the expanded tier.
Sites the answers cite
76 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. 1075 links across 257 sites, every framing counted. Ranked by the number of answers carrying the site or page. None of the 252 answers across every segment cited this index's own page for the category.
34 answers · 50 citations · 12 models
vendor site · Docsumo32 answers · 57 citations · 12 models
vendor site · G230 answers · 70 citations · 13 models
vendor site · Nanonets25 answers · 27 citations · 11 models
vendor site · Guideflow25 answers · 25 citations · 9 models
vendor site · Flowwright24 answers · 26 citations · 8 models
18 answers · 20 citations · 9 models
vendor site · RaftLabs17 answers · 17 citations · 9 models
16 answers · 19 citations · 8 models
vendor site · LarkSuite16 answers · 16 citations · 10 models
vendor site · Lido15 answers · 23 citations · 8 models
15 answers · 18 citations · 7 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.
27 answers · 9 models
27 answers · 11 models
23 answers · 9 models
21 answers · 7 models
18 answers · 9 models
18 answers · 8 models
17 answers · 9 models
16 answers · 10 models
16 answers · 8 models
15 answers · 10 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 | 32% | 84 | 1,900 | 29 | 7,984 | 2 | |
| Rossum rossum.ai | 16% | 101 | 1,600 | 2,838 | 3,120 | 24 | |
| Parseur parseur.com | 8% | 29 | 880 | 9 | 17,087 | ||
| Docsumo docsumo.com | 6% | 73 | 590 | 3 | 12,362 | 0 | |
| Google Cloud parent site Google Document AI 6% | 6% | 72 | 165,000 | 7,596 | |||
| Microsoft parent site Microsoft Entra ID 4%, Microsoft Azure AI Document Intelligence 2% | 6% | 480 | 2,240,000 | 403,136 | |||
| UiPath Document Understanding uipath.com | 4% | 115 | 260 | 6 | 161,995 | $74 | 107 |
| Amazon parent site Amazon Textract 4% | 4% | 74 | 151,000,000 | 1,380,939 | |||
| ABBYY Vantage abbyy.com | 4% | 112 | 210 | 1 | 36,786 | 14 | |
| Lido lido.app | 4% | 14 | 33,100 | 9,264 | 1,134 | 1 |
Google's top ten for the two searches hold 17 sites; 2 of them are among the sites the models cited here (g2.com, gartner.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 4.5Nanonetsno first choiceChangedABBYY Vantageagainst: Azure AI Document Intelligence, Google Document AIAmazon Textractno first choiceagainst: Automation Anywhere IQ Bot, Klippa DocHorizon, Kofax, Nanonets, Tungsten TotalAgility, UiPath Document Understanding
Three alternatives
ABBYY Vantage, Amazon Textract, RossumThree alternatives
Hyperscience Hypercell, Rossum, UiPath Document UnderstandingFour alternatives
Docsumo, Microsoft Azure AI Document Intelligence, Nanonets, UiPath Document UnderstandingGPT-5.4 miniRossumMicrosoft Entra IDChangedUiPath Document UnderstandingGoogle Document AIagainst: ABBYY Vantageno first choiceagainst: ABBYY Vantage, DocuPipe, Graip.AI, LLM Whisperer, Microsoft Azure Document Intelligence, PandaDoc, Unstract
Four alternatives
ABBYY Vantage, Automation Anywhere, Hyperscience Hypercell, UiPath Document UnderstandingTwo alternatives
Okta, Ping IdentityTwo alternatives
Amazon Textract, Microsoft Azure AI Document IntelligenceTwo alternatives
Docparser, DocsumoGemini 3.5 FlashNanonetsagainst: ABBYY Vantage, KofaxNanonetsHeldUiPath Document UnderstandingGoogle Document AI, Microsoft Azure AI Document Intelligence, Nanonetsno first choiceagainst: ABBYY FlexiCapture, Amazon Textract, Automation Anywhere IQ Bot, Azure AI Document Intelligence, Docparser, Google Document AI, Tungsten Automation, UiPath Document Understanding
Three alternatives
Affinda, Docsumo, RossumTwo alternatives
Docsumo, RossumFive alternatives
ABBYY Vantage, Hyperscience Hypercell, LlamaParse, Rossum, Tungsten AutomationFour alternatives
Amazon Textract, Docparser, ImageToTable.ai, ParseurPerplexity SonarNanonetsKlippa DocHorizonChangedABBYY VantageParseuragainst: Amazon Textractno first choicenothing named
Four alternatives
ABBYY Vantage, Automation Anywhere, Rossum, UiPath Document UnderstandingTwo alternatives
Parseur, UiPath Document UnderstandingSix alternatives
Amazon Textract, Instabase, LlamaParse, OpenText Core Capture, Tungsten Automation, UiPath Document UnderstandingThree alternatives
Docsumo, Microsoft AI Builder, NanonetsGrok 4.1 FastABBYY VantageRossumChangedagainst: ABBYY Vantage, Automation Anywhere, UiPath Document Understandingno first choiceParseuragainst: Docling, FormKiQ, Unstructured.iono first choiceagainst: Hyperscience Hypercell
Four alternatives
Amazon Textract, Google Document AI, Rossum, UiPath Document UnderstandingFour alternatives
ABBYY Vantage, Docsumo, Nanonets, ParseurFive alternatives
Amazon Textract, Docparser, Docsumo, Google Document AI, NanonetsMistral SmallRossum, UiPath Document UnderstandingMicrosoft Entra ID, OktaChangedno first choiceLidono first choicenothing named
Three alternatives
Flowwright, Nanonets, OpenText Intelligent Document ProcessingTwo alternatives
Auth0, Ping IdentityOne alternative
FileCenterDeepSeek V4 FlashDocsumo, NanonetsOneLoginChangedABBYY Vantage, Hyperscience HypercellLidoagainst: ABBYY FlexiCapture, Rossumno first choiceagainst: Google Document AI, Instabase
Two alternatives
ABBYY Vantage, RossumThree alternatives
JumpCloud, Microsoft Entra ID, Okta Workforce IdentityEight alternatives
Amazon Textract, Azure AI Document Intelligence, Docsumo, Google Document AI, Nanonets, Rossum, Tungsten Automation, UiPath Document UnderstandingFive alternatives
Amazon Textract, Docsumo, DocuClipper, Google Document AI, NanonetsLlama 4 MaverickNanonetsDocBitsChangedno first choiceRossumno first choicenothing named
Three alternatives
Infrrd, Rossum, UiPath Document UnderstandingOne alternative
Microsoft SyntexQwen 3.7 FlashRossumagainst: ABBYY VantageUiPath Document UnderstandingChangedno first choiceParseuragainst: ABBYY Vantage, Rossum, UiPath Document Understandingno first choiceagainst: ABBYY FlexiCapture, Amazon Textract, Azure AI Document Intelligence, Kofax, UiPath Document Understanding
Two alternatives
Nanonets, UiPath Document UnderstandingThree alternatives
Microsoft Azure Document Intelligence, Rossum, Tungsten AutomationNine alternatives
ABBYY FlexiCapture, ABBYY Vantage, Amazon Textract, Docsumo, Google Document AI, Kofax, Microsoft Azure AI Document Intelligence, Nanonets, UiPath Document UnderstandingThree alternatives
Airparser, Azure AI Document Intelligence, ImageToTable.aiKimi K2NanonetsDocsumo, NanonetsChangedagainst: ABBYY Vantage, Hyperscience Hypercell, UiPath Document Understandingno first choiceDocuClipper, Nanonetsagainst: SimpleOCR / GOCRno first choiceagainst: ABBYY Vantage, UiPath Document Understanding
Three alternatives
ABBYY Vantage, Rossum, UiPath Document UnderstandingOne alternative
RossumSix alternatives
Docparser, EasyOCR, Google Cloud Vision, Parseur, Readiris 17, Tesseract OCRGLM 4.7 FlashXNanonetsNanonetsHeldServiceNowDocsumo, Parseurno first choiceagainst: ABBYY Vantage, Appian, Hyland, IBM, OpenText, Tungsten Automation, UiPath Document Understanding
Two alternatives
DigiParser, RossumThree alternatives
Klippa DocHorizon, Rossum, UiPath Document UnderstandingNine alternatives
ABBYY Vantage, Automation Anywhere, Docsumo, Hyperscience Hypercell, Kofax (Tungsten) TotalAgility, LlamaParse, Nanonets, Rossum, UiPath Document UnderstandingSeven alternatives
Amazon Textract, Azure AI Document Intelligence, Google Document AI, Nanonets, Taggun, Tesseract OCR, UnstractMiniMax M2.5no first choiceNanonets, RossumChangedno first choiceAmazon Textract, Google Document AIno first choiceagainst: Automation Anywhere, UiPath Document Understanding
Six alternatives
ABBYY Vantage, Amazon Textract, Automation Anywhere, Azure AI Document Intelligence, Docsumo, UiPath Document UnderstandingOne alternative
DocBitsThree alternatives
LarkSuite, Microsoft Azure Form Recognizer, UnstractGPT-6 LunaABBYY Vantageagainst: Rossumno first choiceChangedno first choiceNanonetsagainst: Docsumono first choiceagainst: Amazon Textract, Azure AI Document Intelligence, Infrrd, Nanonets, OpenText Core Capture, Tungsten Automation
Two alternatives
Azure AI Document Intelligence, Google Document AIEight alternatives
ABBYY Vantage, Amazon Textract, Automation Anywhere Document Automation, Google Document AI, Microsoft Azure AI Document Intelligence, Rossum, Tungsten Automation, UiPath Document UnderstandingOne alternative
Google Document AIMuse Glimmer 30BRossumagainst: Hyperscience Hypercell, UiPath Document UnderstandingNanonets, RossumChangedABBYY Vantage, Hyperscience HypercellNanonetsagainst: deepdoctectionno first choiceagainst: Azure AI Document Intelligence, formerly Form Recognizer, UiPath Document Understanding
Three alternatives
Doxis AI.dp, Klippa DocHorizon, NanonetsTwo alternatives
Docsumo, UiPath Document UnderstandingFive alternatives
Amazon Textract, Automation Anywhere, Google Document AI, Rossum, UiPath Document UnderstandingOne alternative
Amazon TextractBold 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. Full answer text is in the free responses file. Download the record
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 | 2026-10-05 00:40 | yes | 9 | 8 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 23:52 | yes | 2 | 5 s |
| Direct recommendation | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 23:49 | yes | 15 | 26 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-10-05 00:24 | yes | 19 | 2 s |
| Direct recommendation | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 23:36 | yes | 22 | 10 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 22:21 | yes | 12 | 7 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 01:51 | yes | 22 | 33 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 01:08 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 01:08 | no | 0 | 28 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 23:54 | yes | 16 | 27 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 23:10 | yes | 25 | 42 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 01:16 | yes | 5 | 28 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-10-05 00:58 | yes | 4 | 22 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 22:13 | yes | 23 | 22 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 22:36 | no | 0 | 4 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-04 22:14 | yes | 3 | 4 s |
| Paraphrase | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-04 23:54 | yes | 12 | 23 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-10-05 01:24 | yes | 15 | 3 s |
| Paraphrase | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 00:03 | yes | 22 | 10 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 00:43 | yes | 5 | 4 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-04 22:48 | yes | 21 | 45 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-04 23:44 | yes | 5 | 3 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 01:04 | yes | 15 | 38 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 01:26 | yes | 15 | 35 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-05 00:32 | yes | 23 | 109 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 23:57 | yes | 8 | 16 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-10-05 01:28 | no | 0 | 2 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 01:02 | yes | 14 | 16 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-05 00:20 | yes | 15 | 12 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 01:30 | yes | 5 | 10 s |
| Comparative | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 01:09 | yes | 25 | 28 s |
| Comparative | Perplexity Sonar | sonar | 2026-10-05 01:37 | yes | 19 | 6 s |
| Comparative | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 22:56 | yes | 20 | 12 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-10-04 23:54 | yes | 6 | 9 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 00:43 | yes | 22 | 29 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 01:44 | yes | 5 | 2 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 23:53 | yes | 15 | 27 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 00:26 | yes | 18 | 40 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 22:15 | yes | 19 | 62 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 23:17 | yes | 8 | 20 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-10-05 01:49 | yes | 8 | 21 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 01:36 | yes | 13 | 33 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 22:16 | yes | 9 | 7 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 01:34 | yes | 4 | 5 s |
| Budget constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 01:23 | yes | 21 | 27 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-10-05 01:39 | yes | 19 | 3 s |
| Budget constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-04 22:35 | yes | 24 | 10 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 01:29 | yes | 13 | 7 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 00:32 | yes | 22 | 84 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 01:03 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-04 23:17 | yes | 15 | 39 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 01:17 | yes | 17 | 32 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 23:38 | yes | 24 | 47 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-04 22:53 | yes | 5 | 19 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-10-05 00:04 | yes | 3 | 17 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 23:16 | yes | 20 | 22 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 22:40 | no | 0 | 6 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 00:03 | no | 0 | 12 s |
| Scale constrained | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 00:53 | no | 0 | 16 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-10-04 23:56 | yes | 26 | 5 s |
| Scale constrained | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 00:56 | yes | 18 | 10 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 00:31 | no | 0 | 6 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 00:41 | yes | 24 | 54 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 01:10 | yes | 5 | 2 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 01:02 | no | 0 | 30 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-05 00:40 | yes | 15 | 39 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 23:14 | yes | 23 | 64 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 00:03 | yes | 5 | 30 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-10-05 00:53 | yes | 2 | 23 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-05 00:25 | yes | 14 | 17 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-10-04 23:50 | yes | 18 | 10 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-10-05 01:08 | yes | 3 | 6 s |
| Negative framing | Gemini 3.5 Flash | gemini-3.5-flash | 2026-10-05 00:26 | yes | 8 | 24 s |
| Negative framing | Perplexity Sonar | sonar | 2026-10-05 00:48 | yes | 18 | 3 s |
| Negative framing | Grok 4.1 Fast | spacexai/grok-4.1-fast-non-reasoning via vertex | 2026-10-05 00:45 | yes | 22 | 9 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-10-05 01:21 | yes | 5 | 6 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-10-05 01:29 | yes | 23 | 48 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-10-05 01:34 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-10-05 00:32 | yes | 24 | 68 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-10-04 23:44 | yes | 21 | 23 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-10-04 23:57 | yes | 23 | 53 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-10-05 01:06 | yes | 9 | 26 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-10-05 01:27 | yes | 3 | 28 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-10-04 23:23 | yes | 25 | 30 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 Cloud read as ABBYY Vantage
AWS Textract read as Amazon Textract
Abbyy read as ABBYY Vantage
Google Cloud Document AI read as Google Document AI
Google Cloud Document AI (DocAI) read as Google Document AI
Hyperscience read as Hyperscience Hypercell
Hyperscience (Hypercell) read as Hyperscience Hypercell
Klippa read as Klippa DocHorizon
OpenText Capture read as OpenText Core Capture
UiPath read as UiPath Document Understanding
UiPath (Document Understanding / IXP) read as UiPath Document Understanding
UiPath Document Understanding / IXP read as UiPath Document Understanding
UiPath Document Understanding/IXP read as UiPath Document Understanding
UiPath IXP read as UiPath Document Understanding
UiPath IXP (Intelligent Document Processing) read as UiPath Document Understanding
Unresolved, counted raw
Azure AI Document Intelligence, formerly Form Recognizer
Docling
DocuSign CLM
DocuSign IAM (Intelligent Agreement Management)
EasyOCR
Forage
FormKiQ
Google Cloud Vision
Graip.AI
Ironclad
Kofax (Tungsten) TotalAgility
Krux
LLM Whisperer
Microsoft Form Recognizer
OpenText Intelligent Document Processing
PaddleOCR
Readiris 17
SimpleOCR / GOCR
Sphere
Taggun
Unstructured.io
deepdoctection
Discontinued, still offered
No shut-down product was recommended here.
Follow Intelligent document processing
An email the morning each edition publishes: where this category moved, where it held, and by how much against the noise floor. One address, confirmed by a click; a stop link in every email.
Already following? Everything you follow, with a stop for each.