model-evaluator — Claude Code plugin: what it does, how to install
The model-evaluator plugin for Claude Code assesses and compares machine learning model performance metrics.
Apache-2.0 ★ 2,858 updated 2026-05-12
/plugin marketplace add rohitg00/awesome-claude-code-toolkit
/plugin install model-evaluator@claude-code-toolkitWhat model-evaluator does
The model-evaluator plugin handles evaluation and comparison of ML model performance metrics. It functions inside Claude Code sessions to inspect experimental outputs and benchmark algorithmic results.
Distributed under the Apache-2.0 license, the plugin lives inside the rohitg00/awesome-claude-code-toolkit bundle. Setup requires registering the author's marketplace before running the installation command.
What it helps with
- evaluate machine learning model metrics
- compare performance figures across multiple ML models
- benchmark ML model results inside the CLI
Example prompts for the agent
- Evaluate the performance metrics for this ML model
- Compare the test metrics between both machine learning models
How to install model-evaluator
Plugin marketplace
/plugin marketplace add rohitg00/awesome-claude-code-toolkit/plugin install model-evaluator@claude-code-toolkitStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about model-evaluator
How to install model-evaluator in Claude Code?
Register the repository with /plugin marketplace add rohitg00/awesome-claude-code-toolkit and install the package with /plugin install model-evaluator@claude-code-toolkit.
What does model-evaluator do?
It evaluates and compares performance metrics for machine learning models.
Which license does model-evaluator use?
The plugin is released under the Apache-2.0 license.
Source text
model-evaluator · Apache-2.0
Evaluate and compare ML model performance metrics
© rohitg00 · Apache-2.0 · rohitg00/awesome-claude-code-toolkit