---
title: Session Level Scores
description: Create and manage scores at the session level for more comprehensive evaluation of conversational AI applications
date: 2025-04-28
author: Marlies
ogVideo: https://static.langfuse.com/docs-videos/session_scores.mp4
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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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 session-level scores, enabling comprehensive evaluation of conversational experiences across multiple interactions rather than just individual traces or observations.

## What's New

- **Session-Level Scoring**: Create and manage scores at the session level for holistic evaluation of conversational AI applications
- **Flexible API Design**: Updated APIs to accommodate both trace-level and session-level scoring needs
- **UI Enhancements**: Visual indicators and aggregates for session scores throughout the interface

## API Updates

We have added a new v2 api and will continue to support the v1 api for the foreseeable future.
POST and DELETE APIs will support both trace and session 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**: Either `traceId` or `sessionId` is now required (but not both) when creating scores

## UI Improvements

- **Multi-Level Annotation**: Support for score annotations at trace, observation, and session levels
- **Sessions Table**: Added score aggregates to the sessions table view for quick assessment
- **Consistent Experience**: Unified scoring experience across all levels of your application

## Why Session Scores Matter

Session-level scores are particularly valuable for conversational applications where user satisfaction spans multiple interactions rather than individual exchanges. This enables more accurate evaluation of:

- Overall conversation quality
- Multi-turn interaction effectiveness
- End-to-end user experience metrics

## Get Started

- [Custom Scores Documentation](/docs/evaluation/evaluation-methods/custom-scores)
- [Session Documentation](/docs/observability/features/sessions)

<!-- 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/2025-04-28-session-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>.