{"type":"link","version":"1.0","title":"Towards a Standard, Enterprise-Relevant Agentic AI Benchmark: Lessons from 5.5 billion tokens' worth of agentic AI evaluations","author_name":"AI Archs","author_url":"https://ai-arch.pages.dev","provider_name":"AI Archs","provider_url":"https://ai-arch.pages.dev","url":"https://ai-arch.pages.dev/n/arxiv2511.08042","thumbnail_url":"https://ai-arch.pages.dev/og/arxiv2511.08042.png","thumbnail_width":1200,"thumbnail_height":630}