Library / Building Blocks & Utilities
Building Blocks & Utilities
Benchmark LLMs on Legal Documents with Google Sheets
When triggered manually or by a webhook, it runs legal test questions against OpenRouter and OpenAI models using Drive documents and saves scored results to Google Sheets.
What it does
## Data format Our Tests Sheet contains the following columns: - ID: A unique identifier for each row - Test No.: The test that the LLM was given - AI Platform: The LLM that was given the test. - Relevant Source: The file name of the source document that was given to the LLM. - URL: The Google Drive URL where the file is stored. - Input: The input prompt that the LLM was given. - Output: The response that the LLM gave.
The steps
- When clicking ‘Test workflow’
- Webhook
- Merge1
- Get Tests
- Is PDF?
- Structured Output Parser2
- Basic LLM Chain1
- Google Drive
- Extract from File
- Save Input/Output
- Execute Subworkflow
- OpenRouter Chat Model
- Keep Original Data
- Limit (for testing)
15 steps in total.
Similar automations
Building Blocks & UtilitiesEvaluate LLMs on Legal Questions with OpenRouter12 stepsAI Agents & AssistantsCompare LLMs with OpenRouter and Google Sheets14 stepsCode, Git & Developer ToolsBenchmark Local LLMs in LM Studio, Log to Sheets12 stepsContent Writing & GenerationGenerate llms.txt Files from Screaming Frog Data with OpenAI12 steps