---
title: 'Pydantic Evals Launched: Open-source evals for AI models'
description: >-
  Q1 2025 Highlights: Introducing Pydantic Evals, Pydantic Logfire MCP Server
  and other enhancements for the Pydantic AI platform
date: '2025-04-02'
authors:
  - Samuel Colvin
categories:
  - Pydantic Validation
  - Pydantic Logfire
  - Company
canonical: 'https://pydantic.dev/articles/q1-2025-summary'
---

> Markdown version of [Pydantic Evals Launched: Open-source evals for AI models](https://pydantic.dev/articles/q1-2025-summary) — the canonical HTML page.
>
> By [Samuel Colvin](https://pydantic.dev/authors/samuel-colvin.md) · 2025-04-02 · Pydantic Validation, Pydantic Logfire, Company
>
> Related: [You've built this agent before](https://pydantic.dev/articles/harness-week.md) · [Your traces already know how to fix your prompt](https://pydantic.dev/articles/logfire-prompt-optimization.md)
>
> All articles: [/articles.md](https://pydantic.dev/articles.md) · Site index: [/llms.txt](https://pydantic.dev/llms.txt)

---

We've had an incredibly productive first quarter of 2025, with significant feature enhancements across our entire ecosystem.
Here's a comprehensive overview of what we've shipped:

## Major New Capabilities

### Pydantic Evals
Our new [open-source evaluation framework](https://pydantic.dev/docs/ai/evals/evals/) helps you benchmark and evaluate AI models with optional Pydantic Logfire integration,
making it easier to measure and improve LLM performance.

### Pydantic Logfire MCP Server
Connect your Pydantic AI agents directly to your Pydantic Logfire data through our new [Model Context Protocol integration](https://pydantic.dev/articles/mcp-launch), enabling more intelligent agents with access to your observability data.

### New SDKs
We've expanded our SDK offerings with:
- **[Logfire JS SDK](https://pydantic.dev/articles/js-sdk-launch)**: Official JavaScript/TypeScript SDK for Pydantic Logfire.
- **[Logfire Rust SDK](https://pydantic.dev/articles/rust-sdk-launch)**: Official Rust SDK for Pydantic Logfire.

---

## Enterprise Features

### Pydantic Logfire Enterprise
We've launched both [Self-Hosted and Enterprise Cloud editions](https://pydantic.dev/articles/logfire-self-hosting-announcement) of Pydantic Logfire for organizations with advanced requirements, offering greater control and customization.

### EU Data Region
Store and process your observability data entirely within the [European Union](https://pydantic.dev/articles/eu-region-launch) with our new regional deployment, helping meet data sovereignty and compliance requirements.

### Enhanced Compliance
Pydantic Logfire is now [SOC2 and HIPAA](https://pydantic.dev/docs/logfire/deploy/compliance/) compliant, making it suitable for use in regulated industries including healthcare.

---

## Platform Improvements

### Authentication and Access
- Google Login support for simpler Pydantic Logfire account creation

### LLM Observability
- Enhanced Pydantic AI LLM tracing with token counts and tool call details
- Improved UX for LLM monitoring
- OpenAI agents instrumentation support

Discover how Logfire provides [end-to-end AI observability](https://pydantic.dev/logfire) for your AI applications.

### Data Collection and Processing
- [OTel logs endpoint](https://pydantic.dev/docs/logfire/instrument/opentelemetry-collector/otel-collector-overview/#collecting-system-logs) for unified observability
- Significant query speed optimizations
- Overall user experience enhancements

### Demo and Examples
- Interactive [demo project](https://logfire.pydantic.dev/demo/logfire-demo) showcasing Pydantic Logfire and Pydantic AI capabilities
- Open-source [code examples](https://github.com/pydantic/logfire-demo)

## Core Framework

### Pydantic v2.11
The latest [Pydantic release](https://pydantic.dev/articles/pydantic-v2-11-release) delivers major performance improvements and new features that enhance the developer experience.

### AI Capabilities
Improvements to Pydantic Logfire's English-to-SQL AI functionality for more natural data querying.

---

For more details on any of these updates, please [get in touch](https://pydantic.dev/docs/logfire/get-started/help/). As always, we welcome your feedback as we continue to improve our products.