---
title: What are scores in Langfuse and when should I use them?
description: Understand what scores are, how they differ from tags, and when to use them to evaluate your LLM application.
tags: [evaluation]
---

# What Are Scores and When Should I Use Them?

Scores are covered in detail on the [Evaluation Concepts](/docs/evaluation/scores/overview) page, including:

- [When to use scores](/docs/evaluation/scores/overview#when-to-use-scores) — user feedback, production monitoring, guardrails, experiments
- [Score types](/docs/evaluation/scores/overview#score-types) — numeric, categorical, boolean, and text
- [Score configs](/docs/evaluation/scores/data-model#score-config) — enforce schemas and validate values on ingestion
- [Scores vs tags](/docs/evaluation/scores/overview#scores-vs-tags) — when to use which
- [Score comments](/docs/evaluation/scores/overview#score-comments) — add context to any score

## How to Create Scores

There are four ways to add scores:

- **LLM-as-a-Judge**: Set up [automated evaluators](/docs/evaluation/evaluation-methods/llm-as-a-judge) that score traces based on custom criteria (e.g. hallucination, tone, relevance). These can return numeric, categorical, or boolean (`true` / `false`) scores plus reasoning, and can run on live production traces or on experiment results.
- **Annotation in the UI**: Team members [manually score](/docs/evaluation/evaluation-methods/annotation) traces, observations, or sessions directly in the Langfuse dashboard. Requires a [score config](/faq/all/manage-score-configs) to be set up first.
- **Annotation queues**: Set up [structured review workflows](/docs/evaluation/evaluation-methods/annotation-queues) where reviewers work through batches of traces.
- **Scores via API/SDK**: [Programmatically add scores](/docs/evaluation/evaluation-methods/scores-via-sdk) from your application code — for user feedback, guardrail results, custom evaluation pipelines, or open-ended text feedback.

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/faq/all/what-are-scores.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx langfuse-cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.