Data lab to train frontier models & evaluate agents

The data research company to accelerate AI in the real world

Research

Our research lab aspires to solve humanity’s greatest coordination challenge: deciding where each person should spend their time

CortexRetrievalBench

An evaluation of AI retrieval systems' ability to find and rank authoritative sources for financial research

    Realm: Legal reasoning benchmark

    The standard for evaluating legal reasoning in AI systems

      Realm: Pathology-report reasoning benchmark

      An evaluation of frontier models on extracting pathology-report facts, preserving diagnostic limits, and avoiding unsupported clinical escalation.