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

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.

      Realm: Financial reasoning benchmark

      An evaluation of frontier models on finance reasoning and spreadsheet-grounded analysis