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
Enzymatic and chemical reactions are key for understanding biological processes in cells. Curated databases of chemical reactions exist but these databases struggle to keep up with the exponential growth of the biomedical literature. Conventional text mining pipelines provide tools to automatically extract entities and relationships from the scientific literature, and partially replace expert curation, but such machine learning frameworks often…
The diagnosis of Mendelian disorders requires labor-intensive literature research. Trained clinicians can spend hours looking for the right publication(s) supporting a single gene that best explains a patient’s disease. AMELIE (Automatic Mendelian Literature Evaluation) greatly accelerates this process. AMELIE parses all 29 million PubMed abstracts and downloads and further parses hundreds of thousands of full-text articles in search of information…
Throughout our lives, we as humans acquire an intuitive understanding of our physical environments, a capacity that supports our imagination and planning abilities. Driven by our own curiosity, we learn about object motion and properties via self-curated targeted experiments, that teach us what we do not know. Recently, neural network models have been proposed that learn forward object dynamics from…
We propose a framework for training sequence tagging models with weak supervision consisting of multiple heuristic rules of unknown accuracy. In addition to supporting rules that vote on tags in the output sequence, we introduce a new type of weak supervision, called linking rules, that vote on how sequence elements should be grouped into spans with the same tag. These…
This work formalizes a deep learning baseline for aortic valve classification and outlines a general strategy for using weak supervision to train machine learning models using unlabeled medical images at scale.
While the detection and classification of simple objects encountered during autonomous driving sessions has been widely researched, the detection of complex objects and situations based on the combinations of objects in a scene remains relatively overlooked. This is especially difficult due to the cost of gathering labels for each complex scenario of interest before training a specialized model. To address…
Proposing a framework for integrating and modeling such weak supervision sources by viewing them as labeling different related sub-tasks of a problem, which we refer to as the multi-task weak supervision setting
Outlining a vision for a Software 2.0 lifecycle centered around the idea that labeling training data can be the primary interface to Software 2.0 systems.
As deep learning models are applied to increasingly diverse problems, a key bottleneck is gathering enough high-quality training labels tailored to each task. Users therefore turn to weak supervision, relying on imperfect sources of labels like pattern matching and user-defined heuristics. Unfortunately, users have to design these sources for each task. This process can be time consuming and expensive: domain…
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.
