Cohort 6 · starts October 5
Executive Agent Leadership
Go deep on building and leading agents, and design your organization's agentic operating system.
Sign upExample
Nufar Gaspar's own run, October 1, 2026
This is the page the Benchmark Runner shows after the reveal, saved as it was at the end of the live Frontier Lab. Seven AI options answered five tasks from Nufar's working week. She scored all 35 answers with the names hidden, and an AI judge scored the same answers as a second opinion. Press Reveal the names to see who was who.
It is one person's tasks, one person's judgment, and one run, so it says what fits her work and nothing about yours. The notes are hers, dictated while scoring and lightly edited for reading. The companies, people, and figures in the tasks are made up, and the money amounts in the pricing task are shown in millions so that nobody reads them as real prices. Costs and times are what that run recorded on that day.
Keep going with us
Cohort 6 · starts October 5
Go deep on building and leading agents, and design your organization's agentic operating system.
Sign upCohort 4 · starts October 12
Need to catch up first? Get fluent in using AI and building with AI, for yourself.
Sign up