Model Releases

// Agents' Last Exam // Agents' Last Exam is a living benchmark of over 1,000 economically valuable tasks, built with 250+ industry experts …

// Agents' Last Exam // Agents' Last Exam is a living benchmark of over 1,000 economically valuable tasks, built with 250+ industry experts and mapped to the U.S. federal occupational taxonomy. The ha

DGX agentx-post
model-releasesdair-ai--x

// Agents' Last Exam // Agents' Last Exam is a living benchmark of over 1,000 economically valuable tasks, built with 250+ industry experts and mapped to the U.S. federal occupational taxonomy. The hardest tier sits at a 2.6% average full pass rate across mainstream harnesses and backbones. ALE behaves like a GDP-coverage instrument instead of another test that saturates in a month. Paper: https://arxiv.org/abs/2606.05405 Learn to build effective AI agents in our academy: https://academy.dair.ai/

Source: DAIR.AI (X) | 2026-06-05

Loading related sources…