We develop methods, benchmarks, and training systems that turn expert data into frontier AI
building benchmarks and collaborating with
Featured research
Senior SWE-bench built by Snorkel with Princeton University and UW-Madison
Continual Learning Bench: Evaluating agents that adapt and improve over time
Learning from Less: Measuring the Effectiveness of RLVR in Low Data Compute Regimes
Agents' Last Exam: Challenge and measure AI agents on economically valuable and real-world tasks
SlopCodeBench: A community benchmark measuring code erosion
Harvey’s BigLaw Bench: Research
Terminal-Bench 2.0: Raising the bar for AI agent evaluation
Benchmarking Agents in Insurance Underwriting Environments
Agentic Coding benchmark: Evaluating AI Models on complex, real-world coding tasks
Vision and impact
We help labs advance frontier models by working with domain experts to design and build complex, realistic datasets that drive model performance.
Benchmarking & Evaluation
Build benchmarks that define and advance the AI frontier
Scaling Subject Matter Expertise
Define how subject matter experts encode their knowledge into data
RL, Training, & Data Valuation
Drive dataset development based on feedback from RL and model training
Community and open science
Open benchmarks, conversations, and research for real-world AI performance.
Open Benchmarks Grants
Backed by a $3M commitment, the program funds open-source datasets, benchmarks, and evaluation artifacts that shape how frontier AI systems are built and evaluated.
Benchtalks
Reading Group
DEEP RESEARCH Expertise
Technical advisors and distinguished affiliates
Browse research blogs and academic papers
Snorkel AI held its Foundation Model Summit Jan 17, bringing together 12 presenters and over 600 attendees at 10 virtual sessions. The event drew registrants from across many sectors, including the tech industry, healthcare, and financial services.
Snorkel AI co-founder and CEO Alex Ratner talks with Ananya Kumar about the work he did on improving the effectiveness of foundation models by using contrastive learning, image augmentations, and labeled subsamples.
Researcher Simran Arora tells Snorkel CEO Alex Ratner how she improved foundation model effectiveness by using “Ask Me Anything”-style questions.
More components in an ML lifecycle are designed to run on autopilot, but some tasks require human-in-the-loop ML, an active research topic that has seen an increasing number of publications in the last 10 years.
The recent debut of ChatGPT astounded the public with the power and speed of foundation models, but their enterprise use remains hampered by adaptation and deployment challenges. In the past year, Snorkel AI has researched several ways to overcome those challenges.
The Snorkel AI team will present five research papers advancing weak supervision and programmatic labeling at the NeurIPS 2022 conference that started this week.
Databricks’ Chief Technologist: Data-Centric AI can learn from Data Engineering and ML Engineering in five ways: continuous updates, versioning, code-centric deployment, data privatization and actionable monitoring.
This blog post introduces variants of Precision, Recall, and F1 metrics called Precision Gain, Recall Gain, and F1 Gain. The gain variants have desirable properties such as meaningful linear interpolation of PR curves and a universal baseline across tasks. This post explains what these benefits mean for you, how the gain metrics are calculated and outline some examples for intuitive comparison.
October 8, 2026 | San francisco
A one-day, invite-only summit providing a first look at the benchmarks and research that will shape the frontier.
