The toolkit to test, validate, and evaluate your models and surface, curate, and prioritize the most valuable data for labeling.

NitroML is a modular, portable, and scalable model-quality benchmarking framework for Machine Learning and Automated Machine Learning (AutoML) pipelines.

Benchmarking the ability of large language models to detect semantic conflicts across domains, documents, and evolving knowledge bases.

Adversarial Testing Lab for Agentic Safeguards (ATLAS). A synthetic multi-agent eval environment for adversarial fraud decisioning inspired by Anthropic's Project Deal. Measures how model quality, tool access, and agent orchestration affect attack discovery & defensive recovery, with deterministic evals and realistic customer-friction limits

A model predicts whether a patient will be diagnosed with diabetes

Intro to Machine Learning Project from TripleTen