# Nanonets vs Rossum: which do AI models recommend for document processing, October 2026

IT AI Recommendation Index, October 2026 Edition, Intelligent document processing. Seven of fourteen models named Nanonets first on the direct prompt; four named Rossum. Page: https://it-ai-index.com/it-data/intelligent-document-processing/nanonets-vs-rossum/

| | First-choice share | Rank | Negative rate | Labels | Models naming it |
|---|---|---|---|---|---|
| Nanonets | 32% | #1 of 11 | 6% | 36 | 13 of 14 |
| Rossum | 16% | #2 of 11 | 8% | 37 | 14 of 14 |

## The direct prompt, model by model

- Claude Haiku 4.5: nanonets first (first choices: Nanonets) (alternatives: ABBYY Vantage, Amazon Textract, Rossum)
- Gemini 3.5 Flash: nanonets first (first choices: Nanonets) (alternatives: Affinda, Docsumo, Rossum)
- Perplexity Sonar: nanonets first (first choices: Nanonets) (alternatives: ABBYY Vantage, Automation Anywhere, Rossum, UiPath Document Understanding)
- DeepSeek V4 Flash: nanonets first (first choices: Docsumo, Nanonets) (alternatives: ABBYY Vantage, Rossum)
- Llama 4 Maverick: nanonets first (first choices: Nanonets)
- Kimi K2: nanonets first (first choices: Nanonets) (alternatives: ABBYY Vantage, Rossum, UiPath Document Understanding)
- GLM 4.7 FlashX: nanonets first (first choices: Nanonets) (alternatives: DigiParser, Rossum)
- GPT-5.4 mini: rossum first (first choices: Rossum) (alternatives: ABBYY Vantage, Automation Anywhere, Hyperscience Hypercell, UiPath Document Understanding)
- Mistral Small: rossum first (first choices: Rossum, UiPath Document Understanding) (alternatives: Flowwright, Nanonets, OpenText Intelligent Document Processing)
- Qwen 3.7 Flash: rossum first (first choices: Rossum) (alternatives: Nanonets, UiPath Document Understanding)
- Muse Glimmer 30B: rossum first (first choices: Rossum) (alternatives: Doxis AI.dp, Klippa DocHorizon, Nanonets)
- Grok 4.1 Fast: neither first, one named (first choices: ABBYY Vantage) (alternatives: Amazon Textract, Google Document AI, Rossum, UiPath Document Understanding)
- MiniMax M2.5: neither named (alternatives: ABBYY Vantage, Amazon Textract, Automation Anywhere, Azure AI Document Intelligence, Docsumo, UiPath Document Understanding)
- GPT-6 Luna: neither named (first choices: ABBYY Vantage) (alternatives: Azure AI Document Intelligence, Google Document AI)

## What the models said about Nanonets

- "Nanonets can feel less comfortable when the job demands deep auditability, complex exception handling, or highly variable multi-document workflows" (Claude Haiku 4.5, negative prompt, soft negative)
- "its workflow-based pricing can be complex for buyers seeking stand-alone IDP" (GPT-6 Luna, negative prompt, soft negative)
- "Choose Nanonets if your documents (like invoices) look different every time. Its AI-driven "no-template" model will save you hours of setup." (Gemini 3.5 Flash, budget prompt, first choice)
- "For most small businesses with a limited budget, Nanonets is the easiest start: free $50 credits, no platform fee" (Muse Glimmer 30B, budget prompt, first choice)
- "Nanonets (Best Overall for Mid-Market): Nanonets is incredibly fast to deploy and highly intuitive." (Gemini 3.5 Flash, paraphrase prompt, first choice)

## What the models said about Rossum

- "Avoid enterprise platforms like ABBYY, Rossum, or UiPath for now" (Qwen 3.7 Flash, budget prompt, hard negative)
- "Rossum is worth evaluating, but it was acquired by Coupa on May 12, 2026. I'd check product roadmap, contract terms, and integration support" (GPT-6 Luna, direct prompt, soft negative)
- "dramatically cheaper than enterprise IDP platforms like Rossum ($18,000+/year minimum)" (DeepSeek V4 Flash, budget prompt, soft negative)
- "Rossum is the most cited mid-market pick. Low-code invoice workflows, usable review flows plus workflow automation, from $18,000/year." (Muse Glimmer 30B, direct prompt, first choice)
- "Rossum - Offers low-code invoice workflows and usable review flows plus workflow automation, starting at $18,000/year." (Llama 4 Maverick, budget prompt, first choice)
- "UiPath and Rossum are top choices due to their accuracy, scalability, and ease of integration" (Mistral Small, direct prompt, first choice)

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. Comparisons are drawn for the top eight products in each category. Published under CC BY 4.0; the output is the models' output, and nothing here is a recommendation by the index.