Intelligent document processing for enterprise buyers
Asked as “intelligent document processing platform”, and as “IDP software”, on behalf of an enterprise B2B company. 50 first choices recorded across the direct, paraphrase, budget and scale prompts, fourteen models each. Added to the November 2026 Edition.
Standing · first-choice share
38%
Contested · Hyperscience Hypercell 12%
38ABBYY Vantage12Hyperscience Hypercell12Microsoft Entra ID38others
38% of first choices, contested.
Since October 2026▼−5Since October 2026: 43% → 38%, −5 points. Inside the 11-point floor: within noise.ABBYY Vantage held the lead, −5 points on 43%, 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.Standing →Enterprise
ABBYY Vantage38%Contested▼−5Since October 2026: 43% → 38%, −5 points. Inside the 11-point floor: within noise.This page
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.Standing →EnterpriseABBYY Vantage38%Contested▼−5Since October 2026: 43% → 38%, −5 points. Inside the 11-point floor: within noise.This pageThe standing
Share is the count of first choices across the direct, paraphrase, budget and scale prompts, over all fourteen models, for an enterprise B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrantSince October 2026
01ABBYY Vantage38%6%52endorsed leader▼−5Since October 2026: 43% → 38%, −5 points. Inside the 11-point floor: within noise.43% → 38%
ABBYY Vantage38%6%52endorsed leader▼−5Since October 2026: 43% → 38%, −5 points. Inside the 11-point floor: within noise.43% → 38%02
Hyperscience Hypercell12%7%46accepted challenger▲+8Since October 2026: 4% → 12%, +8 points. Inside the 11-point floor: within noise.4% → 12%
Hyperscience Hypercell12%7%46accepted challenger▲+8Since October 2026: 4% → 12%, +8 points. Inside the 11-point floor: within noise.4% → 12%03
UiPath Document Understanding10%20%55accepted challenger▼−3Since October 2026: 13% → 10%, −3 points. Inside the 11-point floor: within noise.13% → 10%
UiPath Document Understanding10%20%55accepted challenger▼−3Since October 2026: 13% → 10%, −3 points. Inside the 11-point floor: within noise.13% → 10%04
Rossum4%18%40accepted challenger▼−5Since October 2026: 9% → 4%, −5 points. Inside the 11-point floor: within noise.9% → 4%
Rossum4%18%40accepted challenger▼−5Since October 2026: 9% → 4%, −5 points. Inside the 11-point floor: within noise.9% → 4%05
ServiceNow4%18%11accepted challenger▲+2Since October 2026: 2% → 4%, +2 points. Inside the 11-point floor: within noise.2% → 4%
ServiceNow4%18%11accepted challenger▲+2Since October 2026: 2% → 4%, +2 points. Inside the 11-point floor: within noise.2% → 4%06Microsoft Azure AI Document Intelligence2%23%13accepted challenger▲+2Since October 2026: 0% → 2%, +2 points. Inside the 11-point floor: within noise.0% → 2%
Show the five products at 0%, ordered by negative rate
11Google Document AI Lab in the set0%44%27criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
10Amazon Textract0%39%28criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
09Azure AI Document Intelligence0%33%18criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
08
Automation Anywhere0%21%19accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
Automation Anywhere0%21%19accepted challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%07
Tungsten Automation0%6%16accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise.2% → 0%
Tungsten Automation0%6%16accepted challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise.2% → 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 zero times of 52. Lab treatment is defined on the method page; the row is marked, not excluded.
For buyers
Head to headHead-to-head pages are published for mid-market buyers, so these open on mid-market figures, not enterprise.
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 →
0102030405M06
0708A09
A10
G11
Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative50%
Key
01ABBYY Vantage38%
ABBYY Vantage38%02Hyperscience Hypercell12%
Hyperscience Hypercell12%03UiPath Document Understanding10%
UiPath Document Understanding10%04Rossum4%
Rossum4%05ServiceNow4%
ServiceNow4%06Microsoft Azure AI Document Intelligence2%
07Tungsten Automation0%
Tungsten Automation0%08Automation Anywhere0%
Automation Anywhere0%09Azure AI Document Intelligence0%
10Amazon Textract0%
11Google Document AI0%
What they warned about
Two of fourteen models held their first choice under the paraphrase. 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, 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.
Google Document AI
44%
12 of 27 labels negative · 10 of 14 models
“Per-page consumption pricing models make budgeting unpredictable... Prebuilt processors are closed systems with limited customization” Kimi K2, negative prompt
UiPath Document Understanding20%
11 of 55 labels negative · 9 of 14 models · 2 hard negative
“Comparison table: UiPath Document Understanding = ❌ Limited On-Premise Deployment, ❌ No Deterministic/Auditable Outputs” Muse Glimmer 30B, negative prompt
Amazon Textract
39%
11 of 28 labels negative · 9 of 14 models
“Textract tends to produce verbose and sometimes redundant outputs, its performance on visually complex or degraded documents can be inconsistent, and costs can scale quickly” Claude Haiku 4.5, negative prompt
Rossum18%
7 of 40 labels negative · 6 of 14 models · 1 hard negative
“Rossum is another platform frequently mentioned as one to avoid for now” Mistral Small, negative 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
77 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. 907 links across 281 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.
29 answers · 45 citations · 9 models
vendor site · Hypatos24 answers · 32 citations · 9 models
vendor site · G220 answers · 24 citations · 10 models
vendor site · Docsumo19 answers · 23 citations · 10 models
vendor site · ABBYY18 answers · 24 citations · 9 models
17 answers · 17 citations · 7 models
16 answers · 18 citations · 9 models
vendor site · Grooper16 answers · 16 citations · 8 models
15 answers · 24 citations · 8 models
vendor site · Parseur15 answers · 16 citations · 8 models
vendor site · UiPath14 answers · 16 citations · 8 models
publisher (Gane)13 answers · 15 citations · 8 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.
25 answers · 9 models
20 answers · 8 models
17 answers · 7 models
16 answers · 10 models
16 answers · 8 models
14 answers · 6 models
13 answers · 8 models
12 answers · 7 models
10 answers · 6 models
10 answers · 5 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 | Best Google position |
|---|---|---|---|---|---|---|---|---|
| ABBYY Vantage abbyy.com ABBYY Vantage 38%, ABBYY Vantage / FlexiCapture 2%, ABBYY Timeline 2% | 42% | 136 | 210 | 1 | 36,786 | 14 | ||
| Microsoft parent site Microsoft Entra ID 12%, Microsoft Azure AI Document Intelligence 2% | 14% | 499 | 2,240,000 | 403,136 | ||||
| Hyperscience Hypercell hyperscience.ai | 12% | 93 | 10 | 0 | 3,669 | 1 | 5 | |
| UiPath Document Understanding uipath.com | 10% | 120 | 260 | 6 | 161,995 | $74 | 107 | |
| Okta okta.com Okta 6%, Okta Workforce Identity 4% | 10% | 202 | 368,000 | 8,418 | 1,959,740 | 118 | ||
| Rossum rossum.ai | 4% | 125 | 1,600 | 2,838 | 3,120 | 24 | ||
| ServiceNow servicenow.com | 4% | 61 | 135,000 | 13,451 | 689,216 | $673 | 101 | |
| Grooper grooper.com | 2% | 11 | ||||||
| Tungsten TotalAgility | 2% | |||||||
| Tungsten Automation tungstenautomation.com | 0% | 31 | 2,400 | 61 | 37,829 | $741 | 120 |
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 an enterprise B2B company?”Paraphrase“Which IDP software would you recommend to a large B2B company with thousands of employees?”Comparative“What are the top enterprise-grade intelligent document processing platforms and how do they differ?”Budget-constrained“What is the best intelligent document processing platform for a large company that needs predictable total cost across thousands of users?”Scale-constrained“We are a 5,000 person company with SSO, SOC 2 and procurement review requirements evaluating an intelligent document processing platform. What should we look at?”Negative“Which intelligent document processing platforms should a large enterprise avoid or be cautious about?”
Claude Haiku 4.5no first choiceno first choiceHeldno first choiceRossumno first choiceagainst: Amazon Textract, Google Document AI, OpenText Intelligent Capture, UiPath Document Understanding
Two alternatives
ABBYY Vantage, UiPath Document UnderstandingGPT-5.4 miniABBYY VantageABBYY Vantage, UiPath Document UnderstandingChangedABBYY Vantage / FlexiCaptureMicrosoft Azure AI Document Intelligenceagainst: Rossumno first choicenothing named
Three alternatives
Amazon Textract, Google Document AI, UiPath Document UnderstandingThree alternatives
Hyperscience Hypercell, Kofax, RossumTwo alternatives
ABBYY Vantage, UiPath Document UnderstandingGemini 3.5 FlashABBYY Vantage, Hyperscience HypercellHyperscience Hypercell, RossumChangedHyperscience HypercellHyperscience Hypercellagainst: Amazon Textract, Azure AI Document Intelligence, Google Document AIno first choicenothing named
Seven alternatives
Amazon Textract, Indico Data, Infrrd, Microsoft Azure AI Document Intelligence, Rossum, Tungsten Automation, UiPath Document UnderstandingTwo alternatives
ABBYY Vantage / FlexiCapture, Tungsten AutomationSix alternatives
ABBYY Vantage, Indico Data, Instabase, Rossum, Tungsten Automation, UiPath Document UnderstandingTwo alternatives
ABBYY Vantage, UiPath Document UnderstandingPerplexity SonarABBYY Vantageagainst: Amazon Textract, Azure AI Document Intelligence, Google Document AIMicrosoft Entra ID, Okta Workforce IdentityChangedABBYY VantageGrooperagainst: Hyperscience Hypercell, Microsoft Power Automate AI Builder, Parseurno first choiceagainst: Amazon Textract, Azure AI Document Intelligence, Google Document AI, Hypatos, LlamaParse, Nanonets, Rossum, UiPath Document Understanding
Five alternatives
Grooper, Hypatos, Hyperscience Hypercell, Rossum, UiPath Document UnderstandingThree alternatives
CyberArk Identity plus PAM, Google Cloud Identity, Ping IdentitySix alternatives
Amazon Textract, Google Document AI, Hyperscience Hypercell, Microsoft Azure AI Document Intelligence, Rossum, UiPath Document UnderstandingOne alternative
ABBYY VantageGrok 4.20ABBYY Vantage / FlexiCaptureagainst: IBM Watson, OpenText Core CaptureOktaChangedagainst: KeycloakABBYY VantageTungsten TotalAgilityagainst: ABBYY Vantage, Amazon Textract, Automation Anywhere, Google Document AI, Instabase, Microsoft Azure AI Document Intelligence, OpenText, Rossum, UiPath Document Understandingno first choiceagainst: ABBYY Vantage, Automation Anywhere, Microsoft Power Automate, UiPath Document Understanding
Two alternatives
Automation Anywhere, Hyperscience HypercellTwo alternatives
Microsoft Entra ID, Ping IdentityFive alternatives
Hyperscience Hypercell, Indico Data, Rossum, Tungsten Automation, UiPath Document UnderstandingOne alternative
Hyperscience HypercellNine alternatives
ABBYY FlexiCapture, Amazon Textract, Azure AI Document Intelligence, Eigen, Google Document AI, Hyperscience Hypercell, Indico Data, Rossum, UiPath Document UnderstandingMistral SmallABBYY VantageMicrosoft Entra ID, OktaChangedServiceNowABBYY Vantageno first choiceagainst: ABBYY Vantage, Amazon Textract, Google Document AI, Rossum, UiPath Document Understanding
Four alternatives
Hypatos, Microsoft Azure AI Document Intelligence, Rossum, UiPath Document UnderstandingThree alternatives
Google Workspace, OneLogin, Ping IdentitySeven alternatives
ABBYY Vantage, Automation Anywhere, Google Document AI, Hyperscience Hypercell, LlamaParse, Microsoft, UiPath Document UnderstandingThree alternatives
Hyperscience Hypercell, Microsoft Azure AI Document Intelligence, UiPath Document UnderstandingDeepSeek V4 FlashUiPath Document Understandingagainst: Amazon Textract, Google Document AI, Microsoft Azure AI Document IntelligenceMicrosoft Entra IDChangedABBYY Vantage, UiPath Document Understandingagainst: ServiceNowABBYY Vantageagainst: Rossumno first choiceagainst: Affinda, Appian, Automation Anywhere, Blue Prism, Fortra, Hyperscience Hypercell, Kofax, MuleSoft, OpenText, ProcessMaker, Rossum, ServiceNow, Tungsten, UiPath Document Understanding
Four alternatives
ABBYY Vantage, Automation Anywhere, Hyperscience Hypercell, ServiceNowTwo alternatives
Okta, Ping IdentitySeven alternatives
Amazon Textract, Automation Anywhere IQ Bot, Azure AI Document Intelligence, Google Document AI, Hyperscience Hypercell, Rossum, Tungsten AutomationThree alternatives
Hyperscience Hypercell, Kofax, Tungsten AutomationLlama 4 MaverickABBYY Vantageno first choiceChangedno first choiceABBYY Vantageno first choiceagainst: Kolena
Three alternatives
Hyperscience Hypercell, Rossum, UiPath Document UnderstandingThree alternatives
Hyperscience Hypercell, Rossum, UiPath Document UnderstandingQwen 3.7 FlashServiceNow, UiPath Document UnderstandingABBYY Vantage, Microsoft Entra IDChangedABBYY VantageABBYY Vantageagainst: Microsoftno first choiceagainst: Amazon Textract, Automation Anywhere, Azure AI Document Intelligence, Blue Prism, Google Document AI, UiPath Document Understanding, Zapier
Six alternatives
ABBYY FlexiCapture, Automation Anywhere, Hyperscience Hypercell, Microsoft, OpenText, RossumThree alternatives
Microsoft Power Automate, Okta, UiPath Document UnderstandingFour alternatives
Hyperscience Hypercell, Microsoft Copilot for Office & Document Intelligence, Rossum, UiPath Document UnderstandingThree alternatives
Hypatos, Rossum, UiPath Document UnderstandingKimi K2UiPath Document UnderstandingUiPath Document UnderstandingHeldABBYY VantageABBYY Vantage, Hyperscience Hypercellagainst: Microsoft Azure AI Document Intelligenceno first choiceagainst: Amazon Textract, Google Document AI, SAP Document AI
Five alternatives
ABBYY Vantage, Automation Anywhere IQ Bot, Hyperscience Hypercell, Rossum, ServiceNowTwo alternatives
ABBYY Vantage, ServiceNowSeven alternatives
Amazon Textract, Automation Anywhere, Azure AI Document Intelligence, Google Document AI, Hyperscience Hypercell, Tungsten Automation, UiPath Document UnderstandingOne alternative
UiPath Document UnderstandingThree alternatives
Hyperscience Hypercell, Nanonets, RossumGLM 4.7 FlashXServiceNowMicrosoft Entra ID, Okta Workforce IdentityChangedno first choiceHyperscience Hypercellagainst: Azure AI Document Intelligence, Google Document AI, UiPath Document Understandingno first choiceagainst: Hyperscience Hypercell, Rossum, UiPath Document Understanding
Four alternatives
ABBYY Vantage, Automation Anywhere, Hyperscience Hypercell, UiPath Document UnderstandingOne alternative
Ping IdentitySeven alternatives
ABBYY Vantage, Automation Anywhere IQ Bot, Hyperscience Hypercell, Rossum, ServiceNow IDP, Tungsten Automation, UiPath Document UnderstandingOne alternative
ABBYY Vantage / FlexiCaptureMiniMax M2.5ABBYY VantageOktaChangedno first choiceABBYY Timeline, ABBYY Vantageagainst: UiPath Document Understandingno first choicenothing named
Two alternatives
Hyperscience Hypercell, UiPath Document UnderstandingTwo alternatives
Microsoft Entra ID, Ping IdentityTwo alternatives
Grooper, Hyperscience HypercellGPT-6 LunaABBYY Vantageagainst: Amazon Textract, Azure AI Document Intelligence, Google Document AIMicrosoft Entra IDChangedABBYY VantageABBYY Vantageno first choiceagainst: Amazon Textract, Appian's older IDP app, Automation Anywhere IQ Bot Cloud, Google Document AI, Microsoft's document AI building blocks, OpenText Core Capture, Tungsten Automation
Two alternatives
Rossum, UiPath Document UnderstandingTwo alternatives
Okta Workforce Identity, Ping IdentitySeven alternatives
Amazon Textract, Azure AI Document Intelligence, Google Document AI, Hyperscience Hypercell, Rossum, Tungsten TotalAgility, UiPath Document UnderstandingOne alternative
Azure AI Document IntelligenceSix alternatives
ABBYY Vantage, Amazon Textract, Azure AI Document Intelligence, Google Document AI, Hyperscience Hypercell, UiPath Document UnderstandingMuse Glimmer 30BABBYY VantageABBYY Vantage, Hyperscience HypercellChangedABBYY VantageABBYY Vantageno first choiceagainst: Microsoft Power Automate, UiPath Document Understanding, Zapier
Two alternatives
Tungsten Automation TotalAgility, UiPath Document UnderstandingTwo alternatives
Tungsten Automation formerly Kofax TotalAgility, UiPath Document UnderstandingSix alternatives
Hyperscience Hypercell, Microsoft Azure AI Document Intelligence, Rossum, Tungsten Automation Corporation TotalAgility, UiPath Agentic Automation, UiPath Document UnderstandingBold 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 13:33 | no | 0 | 4 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 12:50 | yes | 5 | 5 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 12:56 | yes | 12 | 19 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-11-01 15:42 | yes | 10 | 5 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 18:46 | yes | 5 | 11 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 17:28 | yes | 5 | 4 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 14:40 | yes | 21 | 35 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 13:15 | yes | 5 | 4 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 15:29 | yes | 5 | 31 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 10:53 | yes | 15 | 41 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 11:35 | yes | 15 | 26 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 16:52 | yes | 14 | 39 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-11-01 16:13 | yes | 5 | 17 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:57 | yes | 14 | 16 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 16:29 | no | 0 | 4 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 09:09 | 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 14:10 | yes | 2 | 21 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-11-01 09:35 | yes | 10 | 4 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 19:41 | yes | 10 | 9 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 13:08 | yes | 5 | 5 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 12:19 | yes | 23 | 29 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 14:40 | yes | 5 | 4 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 15:15 | yes | 5 | 31 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 10:48 | yes | 10 | 73 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 10:51 | yes | 15 | 44 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 17:38 | no | 0 | 75 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-11-01 14:25 | yes | 3 | 12 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 13:33 | yes | 14 | 22 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 13:04 | yes | 17 | 13 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 15:02 | yes | 6 | 10 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 18:36 | yes | 9 | 24 s |
| Comparative | Perplexity Sonar | sonar | 2026-11-01 10:20 | yes | 10 | 7 s |
| Comparative | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 16:20 | yes | 12 | 19 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 17:47 | yes | 5 | 10 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 09:09 | yes | 23 | 36 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 15:28 | yes | 5 | 3 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 15:51 | yes | 10 | 50 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 12:48 | yes | 10 | 20 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 14:14 | yes | 25 | 57 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 10:51 | yes | 12 | 28 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:20 | yes | 8 | 28 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 19:18 | yes | 14 | 28 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 13:39 | yes | 19 | 10 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 16:51 | yes | 4 | 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 18:11 | yes | 8 | 23 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-11-01 10:43 | yes | 10 | 4 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 19:33 | yes | 24 | 18 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 12:13 | yes | 5 | 5 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 13:51 | yes | 24 | 31 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 16:10 | yes | 5 | 3 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 15:11 | yes | 5 | 45 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 18:33 | yes | 25 | 44 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 12:18 | yes | 25 | 49 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 11:59 | yes | 5 | 37 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:52 | yes | 2 | 24 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 13:55 | yes | 12 | 22 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 17:07 | yes | 19 | 12 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 18:52 | yes | 4 | 9 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 12:05 | no | 0 | 19 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-11-01 19:31 | yes | 10 | 9 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 14:29 | yes | 5 | 15 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 10:30 | no | 0 | 6 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 14:12 | yes | 22 | 36 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 17:14 | yes | 5 | 4 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 17:13 | no | 0 | 32 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 19:04 | yes | 23 | 44 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 11:52 | yes | 23 | 29 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 19:45 | yes | 19 | 44 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 17:47 | yes | 3 | 25 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 17:51 | yes | 15 | 22 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 16:11 | yes | 15 | 12 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 15:42 | yes | 5 | 8 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 08:39 | yes | 10 | 26 s |
| Negative framing | Perplexity Sonar | sonar | 2026-11-01 13:44 | yes | 10 | 5 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 19:24 | yes | 15 | 17 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 14:28 | yes | 5 | 5 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 10:45 | yes | 25 | 33 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 13:28 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 11:59 | no | 0 | 34 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 15:19 | yes | 25 | 30 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 19:38 | yes | 25 | 101 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 18:27 | yes | 15 | 49 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-11-01 18:51 | yes | 5 | 19 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:45 | yes | 24 | 32 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 (ABBYY Vantage) read as ABBYY Vantage
ABBYY (Vantage & FlexiCapture) read as ABBYY Vantage
AWS Textract read as Amazon Textract
Azure Form Recognizer read as Azure AI Document Intelligence
Google Cloud Document AI read as Google Document AI
Google Cloud Document AI (Prebuilt Processors) read as Google Document AI
Hyperscience read as Hyperscience Hypercell
Hyperscience (Hypercell) read as Hyperscience Hypercell
Microsoft Azure Document Intelligence read as Microsoft Azure AI Document Intelligence
OpenText Capture read as OpenText Core Capture
UiPath read as UiPath Document Understanding
UiPath (Document Understanding / IXP) read as UiPath Document Understanding
UiPath (UiPath Document Understanding / IXP) read as UiPath Document Understanding
UiPath (UiPath IXP / Document Understanding) 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
Unresolved, counted raw
AYR
Appian Low-Court Platform
Appian's older IDP app
Automation Anywhere IQ Bot Cloud
Azinho
CyberArk Identity plus PAM
Document AI
Ephesoft
FlexiCapture
Intellezy
Kyocera
Levvel
Microsoft Copilot for Office & Document Intelligence
Microsoft Document Intelligence
Microsoft Power Automate AI Builder
Microsoft's document AI building blocks
NewgenONE
SS&C Blue Prism Decipher
ServiceNow Document Intelligence
ServiceNow IDP
Textract
Tungsten Automation Corporation TotalAgility
Tungsten Automation TotalAgility
Tungsten Automation formerly Kofax TotalAgility
UiPath Document Intelligence
WorkHQ Platform
Discontinued, still offered
No shut-down product was recommended here.