{"type":"post","id":"epoch-ai-launched-the-inference-performance-index-scoring-1bb9b1","slug":"epoch-ai-launched-the-inference-performance-index-scoring-1bb9b1","title":"Epoch AI launched the Inference Performance Index, scoring chips by real inference capacity, not FLOP/s.","description":"Epoch AI has introduced an Inference Performance Index (IPI) that compares chips by modeled concurrent inference capacity, rather than raw FLOP/s alone.","retrieval_nugget":"Epoch AI has introduced an Inference Performance Index (IPI) that compares chips by modeled concurrent inference capacity, rather than raw FLOP/s alone. Its first version focuses on agentic workloads and estimates large differences between accelerators, highlighting memory, interconnect and output-speed tradeoffs that matter when sizing inference infrastructure.","published_at":"2026-11-10","updated_at":"2026-11-10","record_date":"2026-11-10","date_kind":"published_at","topics":["inference"],"entities":["Epoch AI","Inference Performance Index","Nvidia GB300","Nvidia H100","Nvidia VR200","Nvidia B300 HGX","Nvidia H200 HGX","MI355X"],"related_patterns":["ai-engineering-evaluations-are-splitting-into-task-specific"],"novelty_label":"new_fact","source_url":"https://epoch.ai/publications/inference-performance-index","source_urls":["https://epoch.ai/publications/inference-performance-index"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:epoch-ai-launched-the-inference-performance-index-scoring-1bb9b1","status":"published","visuals":[],"editor":{"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]},"routes":{"html":"https://newruntime.com/posts/epoch-ai-launched-the-inference-performance-index-scoring-1bb9b1/","markdown":"https://newruntime.com/posts/epoch-ai-launched-the-inference-performance-index-scoring-1bb9b1.md","json":"https://newruntime.com/posts/epoch-ai-launched-the-inference-performance-index-scoring-1bb9b1.json"},"markdown_url":"https://newruntime.com/posts/epoch-ai-launched-the-inference-performance-index-scoring-1bb9b1.md","next_reads":[{"type":"topic","path":"/topics/inference/","url":"https://newruntime.com/topics/inference/","title":"Inference","reason":"Explore the inference topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/inference.md","json_url":"https://newruntime.com/topics/inference.json"},{"type":"collection","path":"/posts/","url":"https://newruntime.com/posts/","title":"Field Notes","reason":"Open the latest editorial analysis.","media_type":"text/html","json_url":"https://newruntime.com/posts.json"},{"type":"collection","path":"/sources/","url":"https://newruntime.com/sources/","title":"Sources","reason":"See the original sources this archive cites.","media_type":"text/html"}]}