Benchmarks

Can an agent follow a 100-page company handbook inside an enterprise RL environment?

HANDBOOK.md is a benchmark for long-context agentic instruction following, modeled on how professionals follow corporate policy in their day-to-day work. Each task is a unique RL environment with internal tools and external MCP servers, across five enterprise domains.

A benchmark for the kind of instruction following professional work demands — where constraints depend on each other, fire conditionally, and must be inferred from context.

A real-world AI leaderboard – real prompts, real stakes, graded by experts who read every word, check every citation, and run every line of code.

Today's release benchmarks everyday use. Agentic and enterprise workflows coming soon.

Can frontier models master the documents that run the world? GDP.pdf is a multimodal and reasoning benchmark that takes real-world prompts and PDFs pulled directly from expert professional workflows.

We evaluate AI models on advanced mathematical problems requiring deep reasoning and novel synthesis. Our benchmark features problems from cutting-edge mathematics, sourced from leading mathematicians – Ivy League professors, PhD IMO medalists, graduate students at the top of their field – in the course of their research.

Stop testing models in tiny, self-contained environments. We built CoreCraft, a large-scale startup world, and deployed AI agents to solve real tasks. Our goal: to move agents beyond the cleanliness of the lab and into the chaos of enterprise reality.

Stop rewarding slop. We take real-world writing tasks and put them in front of master wordsmiths. Our goal: to push AI writing from two-second vibes to genuine nuance and impact.