{"type":"post","id":"artificial-analysis-releases-aa-omniscience-v1-1-with-b11513","slug":"artificial-analysis-releases-aa-omniscience-v1-1-with-b11513","title":"Artificial Analysis releases AA-Omniscience v1.1 with a 3,000-question set and new calibrated public subset","description":"Artificial Analysis has updated AA-Omniscience to v1.1, a benchmark for factual recall and hallucination across economically relevant domains.","retrieval_nugget":"Artificial Analysis has updated AA-Omniscience to v1.1, a benchmark for factual recall and hallucination across economically relevant domains. The revised evaluation contains 3,000 questions rather than 6,000 and treats a model’s willingness to abstain as part of reliability, giving builders a more relevant signal than accuracy alone for knowledge-sensitive workflows.","published_at":"2026-10-31","updated_at":"2026-10-31","record_date":"2026-10-31","date_kind":"published_at","topics":["claude","gemini"],"entities":["Artificial Analysis","AA-Omniscience","Gemini 4 Carbon","Claude Opus 5.5","Claude Fable 5.1"],"related_patterns":[],"novelty_label":"new_fact","what_changed":"AA-Omniscience v1.1 now has 3,000 questions across six domains, down from the 6,000-question v1 set, and introduces a smaller calibrated public subset.","prior_refs":["memory:b8a89e19-7571-8feb-af49-16572b1f1cbe","memory:f37d09d2-8572-86fd-a759-5e9b1767dcea"],"source_url":"https://artificialanalysis.ai/evaluations/omniscience","source_urls":["https://artificialanalysis.ai/evaluations/omniscience"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:artificial-analysis-releases-aa-omniscience-v1-1-with-b11513","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/artificial-analysis-releases-aa-omniscience-v1-1-with-b11513/","markdown":"https://newruntime.com/posts/artificial-analysis-releases-aa-omniscience-v1-1-with-b11513.md","json":"https://newruntime.com/posts/artificial-analysis-releases-aa-omniscience-v1-1-with-b11513.json"},"next_reads":[{"type":"topic","path":"/topics/claude/","url":"https://newruntime.com/topics/claude/","title":"Claude","reason":"Explore the claude topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/claude.md","json_url":"https://newruntime.com/topics/claude.json"},{"type":"topic","path":"/topics/gemini/","url":"https://newruntime.com/topics/gemini/","title":"Gemini","reason":"Explore the gemini topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/gemini.md","json_url":"https://newruntime.com/topics/gemini.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":"/source-ledger.json","url":"https://newruntime.com/source-ledger.json","title":"Source Ledger","reason":"Inspect the public source evidence graph.","media_type":"application/json"}]}