Zero of fourteen models named Google Document AI first on the direct prompt; one named UiPath Document Understanding. Google Document AI was named by twelve of the fourteen models and UiPath Document Understanding by fourteen and Google Document AI carries 23 labels and UiPath Document Understanding 46, so the shares are not directly comparable.
Named in one category this edition.
Named in one category this edition.
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; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the intelligent document processing page.
Across every category in the October 2026 Edition, Google Document AI and UiPath Document Understanding were named in the same answer forty-seven times, of the 78 answers naming Google Document AI and the 124 naming UiPath Document Understanding. In those answers UiPath Document Understanding took the first choice three times and Google Document AI one.
| Model | DirectGD | ParaphraseGD | ComparativeGD | Budget-constrainedGD | Scale-constrainedGD | NegativeGD |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | GD | |||||
| GPT-5.4 mini | GD | |||||
| Gemini 3.5 Flash | GD | GD | ||||
| Perplexity Sonar | ||||||
| Grok 4.1 Fast | GD | GD | ||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | GD | GD | GD | |||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | GD | |||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | GD | |||||
| MiniMax M2.5 | GD | |||||
| GPT-6 Luna | GD | GD | GD | |||
| Muse Glimmer 30B | GD |
Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“center on managed analysis APIs, so buyers assemble most of the operational queue, review, routing, and export application around them” Claude Haiku 4.5 · comparative prompt · soft negative
“Users report pricing issues that hinder adoption for smaller businesses; costs can escalate unpredictably” DeepSeek V4 Flash · negative prompt · soft negative
“Google Cloud Document AI” Gemini 3.5 Flash · negative prompt · soft negative
“My practical pick: Google Document AI if you want a strong cloud-native option with a free tier and transparent usage pricing.” GPT-5.4 mini · budget prompt · first choice
“Go with Google Cloud Document AI or Azure AI Document Intelligence. Their free tiers are highly generous” Gemini 3.5 Flash · budget prompt · first choice
“I would suggest starting with Google Cloud Document AI or Amazon Textract” MiniMax M2.5 · budget prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of eight in this category shown.
“Avoid ABBYY/UiPath/Hyperscience unless you have dedicated IT resources” Kimi K2 · paraphrase prompt · hard negative
“Avoid enterprise platforms like ABBYY, Rossum, or UiPath for now” Qwen 3.7 Flash · budget prompt · hard negative
“Avoid if you want simplicity: ABBYY and UiPath” Qwen 3.7 Flash · negative prompt · hard negative
“Best if you want IDP tightly integrated with automation/RPA... Need document extraction + workflow automation? UiPath.” GPT-5.4 mini · comparative prompt · first choice
“Choose UiPath or Tungsten Automation if you need the document extraction to trigger an intricate downstream workflow” Gemini 3.5 Flash · comparative prompt · first choice
“UiPath and Rossum are top choices due to their accuracy, scalability, and ease of integration” Mistral Small · direct prompt · first choice
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.