ModelRefs / Document Processing — Canonical Workflow
Document Processing — Canonical Workflow
Document Processing: provisional AI workflow implementation reference with candidate models, providers, tools, and architecture.
Overview
OCR, classify and extract structured fields from operational documents with confidence-based human review. Document Processing is a provisional implementation reference with candidate models, providers, tools, benchmarks and deployment patterns to validate on the target workload. Operations deployment requires organization-specific access, retention, approval, exception, and audit controls. Integrations with ERP or workflow systems must be validated against the target data, permissions, and failure paths. Outputs remain provisional decision support and require accountable human review before consequential actions.
Implementation profile
| Category | multimodal-models |
|---|---|
| Implementation maturity | production |
| Primary use cases | ocr, extraction |
| Deployment options | managed-api, hybrid |
| Architectures | serverless-api, managed-container, hybrid-private-cloud |
Candidate models with published references
- BGE-M3
- GPT-5
- GPT-5 Mini
- Claude Sonnet 4.5
- Claude Opus 4
- Gemini 3 Pro
- Llama 4 Scout
- DeepSeek R1
- Mistral Large 2
- Command R+
- o3
- o4 Mini
Coverage means the model is a candidate worth evaluating for this workflow, not a ranking or a recommendation. Models whose reference pages are still in review are omitted.
Benchmarks relevant to this workflow
- IFEval — Instruction-following evaluation with verifiable constraints.
- HellaSwag — Commonsense NLI: select the most plausible 4-way continuation of an ActivityNet/WikiHow paragraph.
- MMLU — Massive Multitask Language Understanding — 57 academic and professional subjects.
These are the benchmarks whose task shape bears on this workflow. Each one only describes its own protocol and date, so confirm the harness matches your workload before treating a score as evidence.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Document Processing — Canonical Workflow.