We develop methods, benchmarks, and training systems that turn expert data into frontier AI

Coding agents have moved from tab-complete to teammate. They autonomously inspect repositories, edit files, run commands, diagnose failures, and work through multi-step engineering tasks. That creates a harder reliability problem. A model that only suggests code is easy for a human to evaluate. A coding agent refactoring your repository and testing its own changes is much harder to supervise –…

Software development is iterative, yet agentic coding benchmarks hide design issues through their single-shot setup. Recent iterative benchmarks attempt to remedy this but heavily constrain an agent’s design decision space, making it impossible to faithfully measure how their decisions shape future extensions. We introduce SlopCodeBench, a benchmark of 36 problems and 196 checkpoints where agents repeatedly extend their own solutions….

At our latest Snorkel AI Reading Group, Mayee Chen (Stanford, Hazy Research) stopped by our San Francisco office to walk us through Olmix: A Framework for Data Mixing Throughout LM Development — work she contributed to during her internship at Ai2 on OLMo 3. Olmix tackles one of the messiest, least-documented levers in LLM pre-training: how to set the ratios…

Rubric-based evaluation is widely used in LLM benchmarks and training pipelines for open-ended, less verifiable tasks. While prior work has demonstrated the effectiveness of rubrics using downstream signals such as reinforcement learning outcomes, there remains no principled way to diagnose rubric quality issues from such aggregated or downstream signals alone. To address this gap, we introduce RIFT: RubrIc Failure mode…

Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While previous work has explored the benefits to model reasoning capabilities by scaling both data and compute used for RLVR, these results lack applicability in many real-world settings where…

Deep research—producing comprehensive, citation-backed reports by searching across hundreds of live websites—marks an important frontier for agentic systems. To rigorously evaluate this ability, three principles are essential: tasks should be (1) user-centric, reflecting realistic information needs, (2) dynamic, requiring up-to-date information beyond parametric knowledge, and (3) unambiguous, ensuring consistent interpretation across users. Existing benchmarks fall short of these principles, often…

Since launching the Open Benchmarks Grants, we’ve received more than 100 applications from academic groups and industry labs spanning a wide range of domains and capabilities. As the best benchmarks drive how the field allocates research effort, the bar for benchmarks has risen as well. Here, we share what’s now table stakes for useful benchmarks, and what separates the ones…

Personalizing large language models (LLMs) is essential for delivering tailored interactions that improve user experience. Many exist004 ing personalization methods require fine-tuning LLMs for each user, rendering them pro006 hibitively expensive for widespread adoption. Although retrieval-based approaches offer a more compute-efficient alternative, they still de009 pend on large, high-quality datasets that are not consistently available for all users. To address…

Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of samples. This creates a trade-off that pretraining scaling laws, such as Chinchilla, do not address. We present Train-to-Test (T2) scaling laws that jointly optimize model size, training tokens, and number of inference samples under fixed end-to-end budgets. T2 modernizes pretraining scaling laws…