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
We introduce a benchmark to evaluate the capability of AI to solve problems in theoretical physics, focusing on high-energy theory and cosmology. The first iteration of our benchmark consists of 57 problems of varying difficulty, from undergraduate to research level. These problems are novel in the sense that they do not come from public problem collections. We evaluate our data…
Existing ML benchmarks lack the depth and diversity of annotations needed for evaluating models on business process management (BPM) tasks. BPM is the practice of documenting, measuring, improving, and automating enterprise workflows. However, research has focused almost exclusively on one task– full end-to-end automation using agents based on multimodal foundation models (FMs) like GPT-4. This focus on automation ignores the…
Embodiments introduce an approach to semi-automatically generate labels for data based on implementation of a clustering or language model prompting technique and can be used to implement a form of programmatic labeling to accelerate the development of classifiers and other forms of models. The disclosed methodology is particularly helpful in generating labels or annotations for unstructured data. In some embodiments,…
Objective: We sought to develop a weak supervision-based approach to demonstrate feasibility of post-market surveillance of wearable devices that render AF pre-diagnosis. Materials and Methods: Two approaches were evaluated to reduce clinical note labeling overhead for creating a training set for a classifier: one using programmatic codes, and the other using prompts to large language models (LLMs). Probabilistically labeled notes…
Zero-shot inference is a powerful paradigm that enables the use of large pretrained models for downstream classification tasks without further training. However, these models are vulnerable to inherited biases that can impact their performance. The traditional solution is fine-tuning, but this undermines the key advantage of pretrained models, which is their ability to be used out-of-the-box. We propose ROBOSHOT, a…
Modern artificial intelligence (AI) systems are powered by foundation models. This paper presents a new set of foundation models, called Llama 3. It is a herd of language models that natively support multilinguality, coding, reasoning, and tool usage. Our largest model is a dense Transformer with 405B parameters and a context window of up to 128K tokens. This paper presents…
Large pretrained models can be used as annotators, helping replace or augment crowdworkers and enabling distilling generalist models into smaller specialist models. Unfortunately, this comes at a cost: employing top-of-the-line models often requires paying thousands of dollars for API calls, while the resulting datasets are static and challenging to audit. To address these challenges, we propose a simple alternative: rather…
As a proof-of-concept, we convened an interactive “red teaming” workshop in which medical and technical professionals stress-tested popular large language models (LLMs) through publicly available user interfaces on clinically relevant scenarios. Results demonstrate a significant proportion of inappropriate responses across GPT-3.5, GPT-4.0, and GPT-4.0 with Internet (25.7%, 16.2%, and 17.5%, respectively) and illustrate the valuable role that non-technical clinicians can…
The third Machine Learning for Health (ML4H) symposium was held in person on December 10, 2023, in New Orleans, Louisiana, USA (Parziale et al., 2022). The symposium included research roundtable sessions to foster discussions between participants and senior researchers on timely and relevant topics for the ML4H community.
