Skip to main content
IBM Granite home page
Search IBM Granite documentation...
⌘K
Introduction
Granite Cookbooks and Recipes
Running Sample Code on Colab
Granite Language Cookbook
Prompt Engineering Guide
Fine-tune Granite using Unsloth
Fine-tune Granite
Document Summarization
Langchain RAG
Contract Analysis
Prompt Declaration Language
Granite Vision Cookbook
Multimodal RAG
Granite Speech Cookbook
Voice Assistant
Granite Guardian Cookbook
Risk Detection
HAP Detection
Granite Time Series Cookbook
Fine-tune Granite Time Series
Forecast Energy Demand
Forecast Bike Rentals
Granite Code Cookbook
Text to Python
Text to Shell Script
Agentic AI Cookbook
BeeAI Agent Framework
BeeAI Basics
BeeAI Workflows
BeeAI Requirement Agent
Travel Planner
Model Evaluation Cookbook
Unitxt
Granite as Judge
Additional Cookbooks
Granite Snack Cookbook
Granite Community
Download Granite
IBM Granite home page
Search IBM Granite documentation...
⌘K
Download Granite
Download Granite
Search...
Navigation
Model Evaluation Cookbook
Granite as Judge
Docs
Cookbooks
Playground ↗
Docs
Cookbooks
Playground ↗
Model Evaluation Cookbook
Granite as Judge
Use Granite as an evaluator of predictions created by another model.
In this recipe we will evaluate how relevant an LLM’s answer is to the question asked.
Get started
Explore sample code in a GitHub repo
Try it out
Execute sample code in Colab
Previous
Granite Snack Cookbook
Explore an extensive collection of recipes that showcase the capabilities of Granite models.
Next
⌘I