Humanity's Last Exam

'Humanity's Last Exam' is a benchmark used to evaluate the performance of search agents, specifically assessing their capabilities in high-difficulty tasks.

Papers using Humanity's Last Exam (4)

OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories2026Context Training with Active Information Seeking2026Humanity's Last Exam2025AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis2025