Simple eval for legal benchmarking
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 12 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenRouter Chat Model, Google Drive and Google Sheets.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Get Tests (Google Sheets): uses Google Sheets
- Is PDF? (If): checks a condition and branches into true / false
- Loop Over Items (Loop Over Items (Split in Batches)): loops over the items in batches
- Google Drive: download
- Is a file? (If): checks a condition and branches into true / false
- Extract from File: extracts data from a file (pdf)
- LLM Judge (Basic LLM Chain): sends a prompt to an LLM, with model: OpenRouter Chat Model; output parser: Structured Output Parser
- Update Results (Google Sheets): append
- Wait: waits 0.5 seconds
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (10)
- Manual Trigger
n8n-nodes-base.manualTrigger - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Wait
n8n-nodes-base.wait - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Extract from File
n8n-nodes-base.extractFromFile - Google Drive
n8n-nodes-base.googleDrive - Google Sheets
n8n-nodes-base.googleSheets - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - If
n8n-nodes-base.if
From the author
This workflow demonstrates a simple way to run evals on a set of test cases stored in a Google Sheet. The example we are using comes from an info extraction task dataset, where we tested 6 different LLMs on 18 different test cases. You can see our sample data…