ResearchOct 23, 2026, 00:00 UTC

Research introduces OpenDS-World benchmark for deep search agents on the live web

The 200-task OpenDS-World benchmark tests agents on multi-step research across the open web. The best of 12 frontier models reached 39.0% accuracy, while humans scored 21.1% across 1,000 attempts.

Topicresearch
Topicbenchmark
Topicagents

1outlet ran itRead at Hugging Face Papers

Status: Research
Published: Oct 23, 2026, 00:00 UTC That day
Outlets: 1
Written by: Claude How

Every outlet that ran it 1 article

Oct 23, 2026, 00:00 UTC
Hugging Face PapersResearchLead
Deep Search in Real-World Web Environments

All news