Intelligent document processing for small business buyers
Asked as “intelligent document processing platform”, and as “IDP software”, on behalf of a small 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
42%
Clear leader
42Nanonets29Docsumo06Docparser23others
42% of first choices, clear leader.
Since October 2026↗new leaderNew leader since October 2026: Nanonets (42%) replaces Docsumo (22% then, 29% now), 13 points clear, past the 11-point floor.Nanonets leads at 42%, replacing Docsumo, which led at 22% and stands at 29% now: 13 points clear, past the floor. The verdict moved from contested to clear leader.
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.This pageMid-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.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.This pageMid-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.Standing →The standing
Share is the count of first choices across the direct, paraphrase, budget and scale prompts, over all fourteen models, for a small B2B company. Ordered by share.
ProductFirst-choice shareNegative rateLabelsQuadrantSince October 2026
01Nanonets42%3%58endorsed leader▲+26Since October 2026: 16% → 42%, +26 points. Past the 11-point floor: movement.16% → 42%
Nanonets42%3%58endorsed leader▲+26Since October 2026: 16% → 42%, +26 points. Past the 11-point floor: movement.16% → 42%02
Docsumo29%0%46accepted challenger▲+7Since October 2026: 22% → 29%, +7 points. Inside the 11-point floor: within noise.22% → 29%
Docsumo29%0%46accepted challenger▲+7Since October 2026: 22% → 29%, +7 points. Inside the 11-point floor: within noise.22% → 29%03
Parseur6%0%34accepted challenger▼−6Since October 2026: 12% → 6%, −6 points. Inside the 11-point floor: within noise.12% → 6%
Parseur6%0%34accepted challenger▼−6Since October 2026: 12% → 6%, −6 points. Inside the 11-point floor: within noise.12% → 6%04
Docparser6%0%19accepted challenger▲+2Since October 2026: 4% → 6%, +2 points. Inside the 11-point floor: within noise.4% → 6%
Docparser6%0%19accepted challenger▲+2Since October 2026: 4% → 6%, +2 points. Inside the 11-point floor: within noise.4% → 6%05
Rossum4%40%47criticized challenger=heldSince October 2026: 4% → 4%, ±0 points. Inside the 11-point floor: within noise.4% → 4%
Rossum4%40%47criticized challenger=heldSince October 2026: 4% → 4%, ±0 points. Inside the 11-point floor: within noise.4% → 4%06ABBYY Vantage2%64%42criticized challenger=heldSince October 2026: 2% → 2%, ±0 points. Inside the 11-point floor: within noise.2% → 2%
ABBYY Vantage2%64%42criticized challenger=heldSince October 2026: 2% → 2%, ±0 points. Inside the 11-point floor: within noise.2% → 2%Show the six products at 0%, ordered by negative rate
12
UiPath Document Understanding0%76%29criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
UiPath Document Understanding0%76%29criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%11
Hyperscience Hypercell0%72%18criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%
Hyperscience Hypercell0%72%18criticized challenger=heldSince October 2026: 0% → 0%, ±0 points. Inside the 11-point floor: within noise.0% → 0%09Amazon Textract0%35%34criticized challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise.2% → 0%
07Google Document AI Lab in the set0%33%36criticized challenger▼−8Since October 2026: 8% → 0%, −8 points. Inside the 11-point floor: within noise.8% → 0%
08Azure AI Document Intelligence0%32%25criticized challenger▼−2Since October 2026: 2% → 0%, −2 points. Inside the 11-point floor: within noise.2% → 0%
10Microsoft Azure AI Document Intelligence0%27%11criticized 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 small business.
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
1112Accepted challengerEndorsed leader
0%First-choice share → · lines at 30% share and 25% negative60%
Key
01Nanonets42%
Nanonets42%02Docsumo29%
Docsumo29%03Parseur6%
Parseur6%04Docparser6%
Docparser6%05Rossum4%
Rossum4%06ABBYY Vantage2%
ABBYY Vantage2%07Google Document AI0%
08Azure AI Document Intelligence0%
09Amazon Textract0%
10Microsoft Azure AI Document Intelligence0%
11Hyperscience Hypercell0%
Hyperscience Hypercell0%12UiPath Document Understanding0%
UiPath Document Understanding0%What they warned about
One 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, 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 Vantage64%
27 of 42 labels negative · 11 of 14 models · 9 hard negative
“Enterprise-heavy tools like ABBYY, Hyperscience, UiPath, or big cloud APIs ... are excluded as they often require more dev resources” Grok 4.20, comparative prompt
Rossum40%
19 of 47 labels negative · 11 of 14 models · 4 hard negative
“Pricing and complexity scale toward enterprise users, and it has been flagged as harder for smaller teams to adopt cost-effectively.” DeepSeek V4 Flash, negative prompt
UiPath Document Understanding76%
22 of 29 labels negative · 9 of 14 models · 10 hard negative
“reviewers consistently flag enterprise RPA-tied IDP suites like UiPath Document Understanding and ABBYY Vantage ... as expensive to license, complex to implement” Muse Glimmer 30B, negative prompt
Hyperscience Hypercell72%
13 of 18 labels negative · 7 of 14 models · 9 hard negative
“Avoid quote-based enterprise platforms such as Hyperscience, ABBYY Vantage or Rossum for a tight budget” Muse Glimmer 30B, 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
75 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. 816 links across 229 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 · G241 answers · 68 citations · 13 models
vendor site · Docsumo28 answers · 52 citations · 12 models
vendor site · Nanonets27 answers · 36 citations · 9 models
vendor site · Parseur24 answers · 31 citations · 11 models
24 answers · 24 citations · 10 models
publisher (Gane)19 answers · 20 citations · 8 models
19 answers · 19 citations · 9 models
14 answers · 14 citations · 9 models
13 answers · 13 citations · 7 models
vendor site · Klippa13 answers · 13 citations · 8 models
12 answers · 12 citations · 8 models
11 answers · 13 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.
34 answers · 13 models
24 answers · 10 models
21 answers · 8 models
19 answers · 9 models
18 answers · 7 models
17 answers · 10 models
16 answers · 8 models
13 answers · 7 models
12 answers · 8 models
12 answers · 9 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 | 42% | 103 | 1,900 | 29 | 7,984 | 2 | |
| Docsumo docsumo.com | 29% | 73 | 590 | 3 | 12,362 | 0 | |
| Parseur parseur.com | 6% | 42 | 880 | 9 | 17,087 | ||
| Docparser docparser.com | 6% | 22 | 880 | 6 | 3,199 | 1 | |
| JumpCloud jumpcloud.com | 6% | 365 | 12,100 | 244 | 108,479 | $8,612 | 80 |
| Rossum rossum.ai | 4% | 125 | 1,600 | 2,838 | 3,120 | 24 | |
| Veryfi veryfi.com | 2% | 4 | |||||
| Microsoft parent site Microsoft Entra ID 2%, Microsoft Azure AI Document Intelligence 0% | 2% | 499 | 2,240,000 | 403,136 | |||
| PropelAuth propelauth.com | 2% | 7 | |||||
| ABBYY Vantage abbyy.com | 2% | 136 | 210 | 1 | 36,786 | 14 |
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 small B2B company?”Paraphrase“Which IDP software would you recommend to a small business that sells to other businesses?”Comparative“What are the top intelligent document processing platforms for a small team and how do they differ?”Budget-constrained“What is the best intelligent document processing platform for a small company with a tight budget?”Scale-constrained“We are a 30 person company evaluating an intelligent document processing platform. What should we look at?”Negative“Which intelligent document processing platforms should a small business avoid or be cautious about?”
Claude Haiku 4.5Nanonetsagainst: ABBYY VantageNanonetsHeldNanonetsagainst: ABBYY Vantage, UiPath Document UnderstandingDocsumo, Nanonetsno first choiceagainst: Microsoft Azure AI Document Intelligence, Nanonets, Rossum, UiPath Document Understanding
Three alternatives
Docsumo, Doxis DocHorizon, LidoThree alternatives
Docparser, Docsumo, ParseurSix alternatives
Amazon Textract, Azure AI Document Intelligence, FileCenter, Google Document AI, Lido, RossumTwo alternatives
Docparser, ZenphiGPT-5.4 miniDocsumo, NanonetsABBYY VantageChangedABBYY Vantage, Rossumagainst: Hyperscience HypercellVeryfino first choiceagainst: ABBYY FlexiCapture, Automation Anywhere, Iron Mountain InSight DXP, OpenText Core Capture, SS&C Blue Prism, Tungsten TotalAgility
Four alternatives
ABBYY Vantage, Amazon Textract, Azure AI Document Intelligence, Google Document AIThree alternatives
Microsoft AI Builder, Rossum, UiPath Document UnderstandingThree alternatives
Amazon Textract, Google Document AI, Microsoft Azure AI Document IntelligenceFour alternatives
Amazon Textract, Azure AI Document Intelligence, Docsumo, Google Document AIGemini 3.5 FlashNanonetsagainst: ABBYY FlexiCapture, KofaxDocsumoChangedagainst: Auth0Nanonetsagainst: Hyperscience Hypercell, Kofax, RossumNanonetsagainst: ABBYY Vantage, Rossum, UiPath Document Understandingno first choiceagainst: ABBYY FlexiCapture, Automation Anywhere IQ Bot, Grooper, Hypatos, Hyperscience Hypercell, IBM Datacap, Tungsten Automation, UiPath Document Understanding
Seven alternatives
Amazon Textract, Azure AI Document Intelligence, Docparser, Docsumo, Google Document AI, Parseur, RossumSeven alternatives
Amazon Textract, Clerk, Descope, Google Document AI, Klippa DocHorizon, Rossum, WorkOSSix alternatives
Azure AI Document Intelligence, DigiParser, Docparser, Docsumo, Google Document AI, VeryfiSeven alternatives
Airparser, Amazon Textract, Azure AI Document Intelligence, Docparser, Google Document AI, Lido, ParseurPerplexity SonarParseuragainst: ABBYY VantageRossumChangedagainst: ABBYY Vantage, Tungsten, UiPath Document UnderstandingNanonets, Parseuragainst: ABBYY Vantage, Google Document AI, Rossum, Tungsten TotalAgility, UiPath Document UnderstandingParseuragainst: ABBYY Vantage, Rossumno first choiceagainst: ABBYY Vantage, Amazon Textract, Azure AI Document Intelligence, Google Document AI, Hyperscience Hypercell, Kofax, Rossum, Tungsten Automation, UiPath Document Understanding
Five alternatives
Amazon Textract, Azure AI Document Intelligence, Nanonets, Rossum, UiPath Document UnderstandingThree alternatives
Microsoft Azure AI Document Intelligence, Nanonets, ParseurTwo alternatives
Docsumo, Microsoft Power AutomateFour alternatives
Amazon Textract, Docparser, Lido, NanonetsGrok 4.20Nanonetsagainst: ABBYY Vantage, Amazon Textract, Automation Anywhere IQ Bot, Google Document AI, Hyperscience Hypercell, Microsoft Azure AI Document Intelligence, UiPath Document UnderstandingDocsumoChangedagainst: ABBYY Vantage, Automation Anywhere, Rossum, SAP Document AI, UiPath Document UnderstandingNanonets, Parseuragainst: ABBYY Vantage, Amazon Textract, Azure AI Document Intelligence, Google Document AI, Hyperscience Hypercell, UiPath Document UnderstandingDocsumo, Nanonetsagainst: ABBYY Vantage, Hyperscience Hypercell, Instabase, UiPath Document Understandingno first choiceagainst: ABBYY Vantage, Amazon Textract, Automation Anywhere, Azure AI Document Intelligence, Google Document AI, Hyperscience Hypercell, SAP Document AI, UiPath Document Understanding
Two alternatives
Docsumo, RossumTwo alternatives
Nanonets, ParseurThree alternatives
Docsumo, Rossum, VeryfiFour alternatives
Amazon Textract, Azure AI Document Intelligence, Google Document AI, RossumMistral SmallDocsumo, Nanonetsagainst: Amazon Textract, Google Document AIMicrosoft Entra IDChangedDocsumo, Nanonets, Parseuragainst: Amazon Textract, Google Document AIDocsumo, Nanonetsno first choicenothing named
Two alternatives
ABBYY Vantage, ParseurFour alternatives
JumpCloud, Okta, Rippling, WorkOSTwo alternatives
Microsoft Azure AI Document Intelligence, RossumTwo alternatives
Google Document AI, ParseurDeepSeek V4 FlashDocsumoagainst: ABBYY Vantage, Hyperscience Hypercell, Rossum, UiPath Document UnderstandingJumpCloud, PropelAuthChangedagainst: Auth0, OktaParseuragainst: RossumNanonetsno first choiceagainst: ABBYY Vantage, Automation Anywhere, DocuPipe, Hyperscience Hypercell, Kofax TotalAgility, Rossum, UiPath Document Understanding
Three alternatives
Microsoft Azure AI Document Intelligence, Nanonets, ParseurFive alternatives
Google Workspace, Keycloak, Microsoft Entra ID, SSOJet, WorkOSThree alternatives
Azure AI Document Intelligence, Docsumo, NanonetsTwo alternatives
Docparser, DocsumoLlama 4 MaverickDocsumo, Nanonets, Parseurno first choiceChangedno first choiceDocsumono first choiceagainst: ABBYY Vantage, Amazon Textract, Automation Anywhere, Rossum
Three alternatives
Docparser, Nanonets, ParseurQwen 3.7 FlashDocsumo, Nanonetsagainst: ABBYY VantageRossumChangedagainst: UiPath Document UnderstandingDocsumo, Nanonetsagainst: ABBYY Vantage, UiPath Document UnderstandingDocsumoagainst: ABBYY Vantage, Amazon Textract, Google Document AI, Microsoft Azure AI Document Intelligenceno first choiceagainst: ABBYY Vantage, Kofax, UiPath Document Understandingagainst: ABBYY Vantage, Amazon Textract, Azure AI Document Intelligence, Google Document AI, Rossum, UiPath Document Understanding
Two alternatives
Microsoft Azure AI Document Intelligence, ParseurTwo alternatives
Hypatos, NanonetsFour alternatives
Amazon Textract, Azure AI Document Intelligence, Google Document AI, RossumTwo alternatives
Nanonets, ParseurSix alternatives
Amazon Textract, Azure AI Document Intelligence, Docparser, Google Document AI, Hyperscience Hypercell, RossumKimi K2NanonetsDocparser, NanonetsChangedagainst: ABBYY Vantage, Hyperscience Hypercell, Rossum, UiPath Document UnderstandingDocsumo, Nanonetsagainst: Amazon Textract, Google Document AINanonetsno first choiceagainst: ABBYY Vantage, UiPath Document Understanding
Three alternatives
Docparser, Docsumo, RossumTwo alternatives
Docsumo, DocuWareTwo alternatives
Parseur, RossumThree alternatives
DocuClipper, Google Document AI, Microsoft Azure AI Document IntelligenceGLM 4.7 FlashXDocparser, Nanonetsagainst: ABBYY Vantage, Rossum, UiPath Document UnderstandingJumpCloudChangedNanonetsDocsumono first choicenothing named
Two alternatives
Amazon Textract, ParseurFour alternatives
Auth0 B2B Connect, OneLogin, SSOJet, WorkOSSix alternatives
AWS, Azure, Docsumo, Google Cloud, Rossum, UiPath Document UnderstandingThree alternatives
Google Document AI, Parseur, Xerox EveryDocMiniMax M2.5no first choiceJumpCloudChangedDocsumo, ParseurNanonetsno first choicenothing named
Three alternatives
Docsumo, Microsoft Azure AI Document Intelligence, NanonetsFour alternatives
Microsoft Entra ID, Okta, SSOJet, WorkOSFive alternatives
ABBYY Vantage, Hyperscience Hypercell, Nanonets, Rossum, UiPath Document UnderstandingThree alternatives
Docparser, Docsumo, TaggunGPT-6 LunaNanonetsagainst: RossumDocparserChangedNanonetsagainst: RossumNanonetsno first choiceagainst: ABBYY Vantage, Azure AI Document Intelligence, Nanonets, Rossum
One alternative
Google Document AIThree alternatives
Azure AI Document Intelligence, Docsumo, ParseurTwo alternatives
Azure AI Document Intelligence, Google Document AIMuse Glimmer 30BDocsumoagainst: Amazon Textract, Azure AI Document Intelligence, Google Document AIDocsumo, NanonetsChangedDocparser, Parseuragainst: RossumNanonetsagainst: ABBYY Vantage, Amazon Textract, Azure AI Document Intelligence, Google Document AI, Hyperscience Hypercell, Rossumno first choiceagainst: ABBYY Vantage, Automation Anywhere, Azure AI Document Intelligence, Hyperscience Hypercell, UiPath Document Understanding
Three alternatives
Nanonets, Parseur, RossumThree alternatives
Azure AI Document Intelligence, Docparser, ParseurTwo alternatives
Docsumo, NanonetsOne alternative
DocsumoBold 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 12:27 | yes | 19 | 9 s |
| Direct recommendation | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 11:27 | 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 13:15 | no | 0 | 16 s |
| Direct recommendation | Perplexity Sonar | sonar | 2026-11-01 16:10 | yes | 10 | 4 s |
| Direct recommendation | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 14:31 | yes | 15 | 15 s |
| Direct recommendation | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 10:10 | yes | 5 | 5 s |
| Direct recommendation | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 19:28 | yes | 20 | 25 s |
| Direct recommendation | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 10:48 | yes | 5 | 2 s |
| Direct recommendation | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 14:44 | yes | 5 | 28 s |
| Direct recommendation | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 13:24 | yes | 10 | 20 s |
| Direct recommendation | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 13:54 | yes | 14 | 50 s |
| Direct recommendation | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 16:41 | yes | 5 | 26 s |
| Direct recommendation | GPT-6 Luna | gpt-6-luna | 2026-11-01 08:57 | yes | 3 | 16 s |
| Direct recommendation | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:10 | yes | 13 | 18 s |
| Paraphrase | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 13:39 | yes | 16 | 8 s |
| Paraphrase | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 08:36 | yes | 4 | 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 12:57 | no | 0 | 14 s |
| Paraphrase | Perplexity Sonar | sonar | 2026-11-01 16:20 | yes | 10 | 3 s |
| Paraphrase | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 18:31 | yes | 12 | 10 s |
| Paraphrase | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:15 | yes | 5 | 5 s |
| Paraphrase | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 09:25 | yes | 25 | 19 s |
| Paraphrase | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 15:31 | yes | 5 | 2 s |
| Paraphrase | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 13:34 | yes | 12 | 107 s |
| Paraphrase | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 12:30 | yes | 15 | 32 s |
| Paraphrase | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 15:15 | yes | 24 | 66 s |
| Paraphrase | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 17:43 | yes | 15 | 54 s |
| Paraphrase | GPT-6 Luna | gpt-6-luna | 2026-11-01 16:49 | yes | 3 | 12 s |
| Paraphrase | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 09:03 | yes | 23 | 30 s |
| Comparative | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 13:01 | yes | 10 | 8 s |
| Comparative | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 10:15 | yes | 6 | 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 12:44 | yes | 10 | 27 s |
| Comparative | Perplexity Sonar | sonar | 2026-11-01 11:27 | yes | 10 | 6 s |
| Comparative | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 17:16 | yes | 9 | 16 s |
| Comparative | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 10:18 | yes | 5 | 7 s |
| Comparative | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 18:05 | yes | 23 | 47 s |
| Comparative | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 08:59 | yes | 5 | 3 s |
| Comparative | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 17:39 | yes | 5 | 44 s |
| Comparative | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 12:07 | yes | 9 | 19 s |
| Comparative | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 18:38 | yes | 23 | 242 s |
| Comparative | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 09:27 | yes | 5 | 26 s |
| Comparative | GPT-6 Luna | gpt-6-luna | 2026-11-01 19:17 | yes | 5 | 21 s |
| Comparative | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 16:37 | yes | 13 | 26 s |
| Budget constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 13:03 | yes | 17 | 9 s |
| Budget constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 15:33 | yes | 5 | 7 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 13:16 | yes | 11 | 21 s |
| Budget constrained | Perplexity Sonar | sonar | 2026-11-01 10:56 | yes | 10 | 4 s |
| Budget constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 15:04 | yes | 5 | 8 s |
| Budget constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 16:13 | yes | 5 | 4 s |
| Budget constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 14:15 | yes | 25 | 25 s |
| Budget constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 09:05 | yes | 5 | 2 s |
| Budget constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 16:32 | yes | 5 | 36 s |
| Budget constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 18:38 | yes | 15 | 40 s |
| Budget constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 18:56 | yes | 25 | 212 s |
| Budget constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 09:23 | yes | 10 | 21 s |
| Budget constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:38 | yes | 2 | 15 s |
| Budget constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 18:04 | yes | 15 | 18 s |
| Scale constrained | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 10:02 | no | 0 | 6 s |
| Scale constrained | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 08:59 | no | 0 | 6 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 12:50 | no | 0 | 16 s |
| Scale constrained | Perplexity Sonar | sonar | 2026-11-01 15:28 | yes | 10 | 5 s |
| Scale constrained | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 14:20 | yes | 10 | 13 s |
| Scale constrained | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 17:47 | no | 0 | 7 s |
| Scale constrained | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 11:25 | yes | 10 | 29 s |
| Scale constrained | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 14:21 | yes | 5 | 3 s |
| Scale constrained | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 16:30 | yes | 5 | 20 s |
| Scale constrained | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 14:32 | yes | 15 | 22 s |
| Scale constrained | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 10:43 | no | 0 | 14 s |
| Scale constrained | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 14:25 | no | 0 | 63 s |
| Scale constrained | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:39 | yes | 1 | 17 s |
| Scale constrained | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 12:31 | yes | 13 | 28 s |
| Negative framing | Claude Haiku 4.5 | claude-haiku-4-5-20251001 | 2026-11-01 09:26 | yes | 16 | 10 s |
| Negative framing | GPT-5.4 mini | gpt-5.4-mini-2026-03-17 | 2026-11-01 12:51 | yes | 6 | 5 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 16:36 | yes | 8 | 24 s |
| Negative framing | Perplexity Sonar | sonar | 2026-11-01 17:42 | yes | 10 | 5 s |
| Negative framing | Grok 4.20 | spacexai/grok-4.20-non-reasoning via xai | 2026-11-01 19:07 | yes | 14 | 10 s |
| Negative framing | Mistral Small | mistral/mistral-small via mistral | 2026-11-01 11:55 | yes | 5 | 5 s |
| Negative framing | DeepSeek V4 Flash | deepseek/deepseek-v4-flash via deepinfra | 2026-11-01 08:35 | yes | 21 | 25 s |
| Negative framing | Llama 4 Maverick | meta/llama-4-maverick via bedrock | 2026-11-01 14:41 | yes | 5 | 3 s |
| Negative framing | Qwen 3.7 Flash | alibaba/qwen3.7-flash via alibaba | 2026-11-01 19:43 | yes | 5 | 27 s |
| Negative framing | Kimi K2 | moonshotai/kimi-k2 via novita | 2026-11-01 19:43 | yes | 17 | 55 s |
| Negative framing | GLM 4.7 FlashX | zai/glm-4.7-flashx via zai | 2026-11-01 15:58 | yes | 22 | 50 s |
| Negative framing | MiniMax M2.5 | minimax/minimax-m2.5 via minimax | 2026-11-01 15:18 | no | 0 | 26 s |
| Negative framing | GPT-6 Luna | gpt-6-luna | 2026-11-01 11:12 | yes | 4 | 18 s |
| Negative framing | Muse Glimmer 30B | meta/muse-glimmer-30b via togetherai | 2026-11-01 17:28 | 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 (FlexiCapture / Intelligent Document Processing / Vantage) 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
Hyperscience read as Hyperscience Hypercell
Klippa read as Klippa DocHorizon
Microsoft Azure Document Intelligence read as Microsoft Azure AI Document Intelligence
Microsoft Azure Form Recognizer read as Microsoft Azure AI Document Intelligence
Microsoft Form Recognizer read as Microsoft Azure AI Document Intelligence
OpenText Capture read as OpenText Core Capture
UiPath read as UiPath Document Understanding
UiPath (Document Understanding / Agentic Automation) read as UiPath Document Understanding
UiPath IXP read as UiPath Document Understanding
Unresolved, counted raw
Automation Anywhere's SMB products
Azure Doc Intelligence
ClickUp Docs AI
Comprehend
Doxis AI (dp)
Iron Mountain InSight DXP
Konfuzio
Microsoft Power Automate's AI Builder
Procys
Sensible AI
Softworks AI
Taggun
Xerox EveryDoc
Xerox EveryDoc App
Discontinued, still offered
No shut-down product was recommended here.