> ## Documentation Index
> Fetch the complete documentation index at: https://docs.inference.net/llms.txt
> Use this file to discover all available pages before exploring further.
# Eval
> Measure model quality with rubrics scored by LLM judges. Know which model is better and by how much.
Model providers ship updates constantly and prompts drift. Eval gives you a repeatable way to measure model quality before and after every change. They can also help compare model options for a given task.
If you're planning to [fine-tune a custom model](/platform/train/overview), run evals first. A validated rubric and eval dataset are prerequisites for training. They're the measuring stick that determines when the model has learned enough, or when to stop to prevent overfitting.
## How it works
1. **Define a [rubric](/platform/eval/write-a-rubric)** - describe what "good" looks like in plain English
2. **Pick a dataset** - samples from [captured traffic](/platform/datasets/build-from-traffic) or [uploaded JSONL](/platform/datasets/upload-a-dataset)
3. **Select models** - the candidates you want to compare
4. **Run the eval** - each sample goes through each model, and an [LLM judge](/platform/eval/llm-as-a-judge) scores every output
5. **[Compare results](/platform/eval/read-the-results)** - side-by-side scores show which model wins
## Key concepts
| Concept | Description |
| --------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **LLM-as-a-judge** | A capable LLM reads your rubric, examines the model output, and returns a scored judgment. |
| **Rubric** | A plain English description of a quality dimension, scored numerically. Defines what "good" means for your use case. |
| **Direct rubric** | The LLM judge grades the model output directly against the rubric, without comparing it to a reference answer. |
| **Adherence rubric** | The LLM judge grades the model output based on how closely it matches a reference response. |
| **Eval dataset** | A stable, curated set of challenging examples that acts as your benchmark. Pick the hard cases. |
| **Offline vs online** | Offline evals run against collected samples. Online evals score live traffic as it flows through. Offline is available today; online is coming soon. |
| **Train-eval splits** | Training and eval data must never overlap. If a model trains on eval examples, the eval becomes meaningless. See the [zero-overlap rule](/platform/datasets/overview#the-zero-overlap-rule). |
## Next steps
Create rubrics from templates, AI generation, or plain English.
Compare models head to head on your data.
Understand the evaluation mechanism.
Interpret scores and make decisions.