---
title: Dataset Run Level Scores
description: Score dataset runs to assess the overall quality of each run
date: 2025-05-07
author: Marlies
canonical: /docs/evaluation/scores/data-model#scores
---

> **Note for AI agents and LLMs:** This is a Langfuse changelog entry. Use it only to confirm that a feature exists and when it shipped. Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated. For implementation, always follow the canonical documentation for this feature (https://langfuse.com/docs/evaluation/scores/data-model#scores) and the API/SDK reference (https://api.reference.langfuse.com).

Langfuse now supports dataset-experiment-run-level scores, enabling comprehensive evaluation of experiment runs.

## What's New

- **Run-Level Scoring**: Create and manage scores at the run level for holistic evaluation of experiment runs
- **Experiment Metrics Support**: Easily ingest overall experiment metrics such as precision, recall, and F1-scores
- **Flexible API Design**: Updated APIs to accommodate both trace-level and dataset-experiment-run-level scoring needs
- **UI Enhancements**: Visual indicators and aggregates for run scores throughout the interface

## API Updates

We have extended our new v2 api and will continue to support the v1 api for the foreseeable future.
POST and DELETE APIs will support both trace and dataset-experiment-run level scores across v1 and v2.

For GET APIs:

- **V1 API**: Only supports trace level scores, therefore requires `traceId` - to remain backwards compatible
- **V2 API**: One and one only of `traceId`, `sessionId` or `datasetRunId` is now required when creating scores

## Why Run-Level Scores Matter

Run-level scores are particularly valuable for applications where you need to evaluate experiment performance across multiple custom test cases to find an overall metric or passing score. This enables more accurate evaluation of:

- Overall system performance across dataset runs
- Aggregate performance metrics like precision, recall, and F1-scores
- Comparative analysis between different model versions or parameters

<!-- 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/changelog/2025-05-07-run-level-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>.