Who founded LLM Stats?

LLM Stats was founded by Jonathan Chávez, Sebastian Crossa in 2025.

Who are LLM Stats's investors?

LLM Stats's investors include Y Combinator, Capitalize VC, Hi Ventures.

Where is LLM Stats headquartered?

LLM Stats is headquartered in New York City, US.

LLM Stats

YC S25

New York City, US · Founded 2025 · 2 employees · 3 known investors

Find your way into LLM Stats

Paths you didn't know you had: your email and LinkedIn already hold routes to the LLM Stats team. We find them for you
2nd- and 3rd-degree connections: the friend-of-a-friend routes that take hours to manually find through your inbox or LinkedIn
Answers now, not in days: momentum is everything in a raise. Skip asking around whether someone knows someone

Days of research, done the moment you sign in, with every route ranked by how warm it is.

llm-stats.com provides open, reproducible evaluation and benchmarking infrastructure for large language models and AI systems. The platform aggregates 200+ benchmarks and enables performance comparisons across frontier AI models to support informed decision-making by researchers, enterprises, and model developers.

Also known as ZeroEval Inc. · CallingBox · ZeroEval · ZeroEval, CallingBox

AI & Machine Learning Data & Infrastructure Developer Tools Enterprise Software Infrastructure AIUnited States of AmericaAmerica / Canada

Founders & leadership· Y Combinator alumni (S25)

LLM Stats was founded in 2025 by Jonathan Chávez and Sebastian Crossa.

Jonathan Chávez Co-FounderJonathan Chávez previously worked as an early employee on the LLM Observability team at Datadog and founded LLM-Stats.com. He has conducted undergraduate research in computer vision and machine learning, including work on Vision Transformers for particle physics applications and reinforcement learning for robotics.

Sebastian Crossa Co-FounderSebastian Crossa is a founding engineer who has worked at Micro, an email infrastructure company backed by a16z, and Atrato Pago (W21), a fintech startup. He co-founded LLM Stats.

Investors · 3

Y Combinatorlisted by Y CombinatorSan Francisco · $500K

How we know: the Y Combinator directory · open dataset · 5k.vc investor directory · Not right? Tell us

Capitalize VCreportedChicago · $100K – $200K

How we know: Y Combinator's founder network · Not right? Tell us

Hi VenturesreportedMexico City · $1M – $5M

How we know: Y Combinator's founder network · Not right? Tell us

Related companies · 10

Hugging FaceHugging Face is a collaboration platform that hosts and provides access to machine learning models, datasets, and applications. It offers both open-source tools for the ML community and paid compute and enterprise solutions for teams building AI applications.

SIDSID trains agentic search models that improve search accuracy and performance on complex search tasks by providing better contextual understanding. The company develops AI models designed to connect intelligence to the world through advanced search capabilities.

OpenRouterOpenRouter operates an AI gateway that allows developers to access and compare hundreds of language models from multiple providers in a single platform. The service eliminates vendor lock-in while offering improved pricing, uptime, and reliability for companies and developers.

SixtyfourSixtyFour provides AI agents that conduct deep research on people and companies by autonomously gathering and cross-referencing data from multiple sources including official records and the web. The platform delivers structured intelligence profiles for threat detection, talent recruitment, and compliance investigations.

LumeLume built software to automate customer data integration for engineering teams, using AI to discover schemas, map data, validate quality, and generate code automatically. The company has closed operations.

DataCampDataCamp is a learning platform for teams that teaches data and AI skills through hands-on coursework accessible via web browser and mobile app. It serves enterprise customers and development teams seeking to build technical capabilities.

ApproximaApproxima provides AI agents that handle routine software development tasks including scoping work, writing code, validating fixes in isolated environments, and deploying to production, freeing developers to focus on novel work.

OpenAIOpenAI is an AI research and deployment company focused on developing artificial general intelligence (AGI) with emphasis on safety and beneficial outcomes for humanity.

OllamaOllama provides a platform for building with and running open-source language models locally and in the cloud. It enables developers to quickly deploy and access models like Claude Code and OpenClaw.

VellumVellum builds AI development tools and platforms for teams building AI applications. The company focuses on helping customers navigate the rapidly evolving AI landscape through products and expertise.

Companies working in the same space as LLM Stats.

Legal entities · 1

corporate structure

ZeroEval Inc.

In the news

ZeroEval - Build self-improving agentsycombinator.com · Aug 2025

Frequently asked questions

What does LLM Stats do?: llm-stats.com provides open, reproducible evaluation and benchmarking infrastructure for large language models and AI systems. The platform aggregates 200+ benchmarks and enables performance comparisons across frontier AI models to support informed decision-making by researchers, enterprises, and model developers.
Who founded LLM Stats?: LLM Stats was founded by Jonathan Chávez, Sebastian Crossa in 2025.
Who are LLM Stats's investors?: LLM Stats's investors include Y Combinator, Capitalize VC, Hi Ventures.
Where is LLM Stats headquartered?: LLM Stats is headquartered in New York City, US.