ModelRefs / Invoice Extraction — Canonical Workflow
Invoice Extraction — Canonical Workflow
Invoice Extraction: provisional AI workflow implementation reference with candidate models, providers, tools, and architecture.
Overview
Invoice extraction pulls candidate fields — vendor, amounts, line items, tax, dates — from authorized PDF and email invoices, with source traceability and validation rules so every extracted value can be checked against the original document before it reaches accounts payable.
Use this page to check what field-level accuracy, layout coverage, and human-review checkpoints an invoice-extraction workflow needs for your vendor mix, then review the related model, tool, and architecture references before implementation.
Representative-workload evidence matters here — extraction accuracy varies by layout, scan quality, language, currency, and tax format. ModelRefs has a drafted evaluation protocol for this workflow but no recorded validated run results yet, so evaluate accuracy on your own invoice sample and keep human review in the loop before any AP action.
Implementation profile
| Category | multimodal-models |
|---|---|
| Implementation maturity | enterprise |
| Evidence status | partial |
| 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 Opus 4
- Llama 4 Scout
- DeepSeek R1
- Mistral Large 2
- Command R+
- o3
- o4 Mini
- Text Embedding 3 Large
- Claude Sonnet 4
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
miracl, mkqa, mldr, swe-bench, aider-polyglot, gpqa, aime-2025, tau-bench, browsecomp-long-context, longfact-concepts, terminal-bench, mmmu, mmlu-pro, livecodebench.
Relevance is a coverage signal from the canonical registry. Each benchmark 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 Invoice Extraction — Canonical Workflow.