--- date: 2026-10-19 title: Experiments show which metric moved, and why description: Chart every score across experiment runs, read summary statistics against your baseline, and compare candidates item by item filtered by score thresholds. author: Marlies ogVideo: https://static.langfuse.com/docs-videos/experiments-metrics.mp4 --- > **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 Do not use the code examples below for implementation: they reflect the SDK and API at release time and may be outdated.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 current documentation (https://langfuse.com/docs) and the API/SDK reference (https://api.reference.langfuse.com). The Experiments page now shows the trade-off between quality, cost, and latency across your runs: - **Charts:** Plot relevant metrics across runs side-by-side. Visualize and compare the trade-off between different metrics. Customize the layout to your needs. - **Summary statistics:** Comparing a candidate run against your baseline? View summary statistics for each score across runs. Assess what improved, what regressed, and trade-off movements. Found a regression? Compare the candidate run against your baseline item by item: - **Score thresholds:** Filter to items under a threshold within a run or across all, so you land on the regressions immediately. - **Layout:** Choose which metrics to show as columns and set the row height, so long outputs are readable in the table. - **Annotate, correct, comment:** Step through items with keyboard shortcuts and add a human score, a corrected output, or a comment without leaving the context of your experiment comparison. ## Get started Open **Experiments** and add a chart for each metric you care about. To go item by item, select two or more runs and compare them. New to experiments? Start with the [Academy guide](/academy/experiments) or see how to [optimize agent cost](/academy/experiments/cost-optimization) with experiments. - [Compare experiments](/docs/evaluation/experiments/compare-experiments) - [Add scores to experiments](/docs/evaluation/evaluation-methods/scores-via-ui#add-scores-to-experiments) - [Scores via SDK](/docs/evaluation/evaluation-methods/scores-via-sdk) --- ## 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/2026-10-19-experiments.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**: , 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 `) to read or write traces, prompts, datasets, and scores from the terminal. Found an error in these docs? Please open an issue at .