New Snorkel benchmark leaderboards. See the results.
AI accelerated through cutting edge science
Our research team partners with world-leading organizations to develop new advancements in data-centric AI that powers production systems across a wide range of organizations and government agencies.
Browse blog posts, patents, and 100+ peer reviewed academic papers published on data-centric AI and foundation models.
Research Paper
Foundation Models Can Robustify Themselves, For Free
Read more
Research Paper
Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models
Read more
Research Paper
On the Opportunities and Risks of Foundation Models
Read more
Research Paper
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
Read more
Research Paper
Measure what matters: Counts of hospitalized patients are a better metric for health system capacity planning for a reopening
Read more
Research Paper
Shrinking the Generation-Verification Gap Weak With Verifiers
Read more
Research Paper
Systems and Methods for Programmatic Labeling of Training Data for Machine Learning Models via Clustering and Language Model Prompting
Read more
Research Paper
Scalable Approach to Medical Wearable Post-Market Surveillance
Read more
Research Paper
Zero-Shot Robustification of Zero-Shot Models with Foundation Models
Read more
Research Paper
The ALCHEmist: Automated Labeling 500x CHEaper Than LLM Data Annotators
Read more
Research Paper
Red Teaming Large Language Models in Medicine: Real-World Insights on Model Behavior
Read more
Featured Benchmarks
Exclusive to Snorkel, these benchmarks are meticulously designed and validated by subject matter experts to probe frontier AI models on demanding, specialized tasks.
SnorkelUnderwrite
An expert-verified frontier benchmark with multi-turn conversations, focused on agentic reasoning and tool use in commercial underwriting settings.
View All Results
Finance Reasoning
A benchmark co-created with Snorkel's financial expert network, to test agents on financial reasoning questions, through tool-calling and planning.
View All Results
SnorkelSequences
A procedurally-generated and expert-verified benchmark for evaluating mathematical reasoning and compositional capabilities in LLMs.
View All Results
Deep research roots
Born out of the Stanford AI lab in 2019 and in collaboration with leading research institutions, Snorkel-affiliated researchers have published more than 170 peer-reviewed research papers on weak supervision, AI data development techniques, foundation models, and more — with special recognition at events such as NeurlPS, ICML, and ICLR. Our researchers are closely affiliated with academic institutions including Stanford University, University of Washington, Brown University, and the University of Wisconsin-Madison
Join the Snorkel Research Team
Join our team of leading researchers and help shape the future of AI.
View all careers