{"type":"post","id":"artificial-analysis-launches-hle-diamond-leaderboard-as-part-0fef9e","slug":"artificial-analysis-launches-hle-diamond-leaderboard-as-part-0fef9e","title":"Artificial Analysis launches HLE-Diamond leaderboard as part of Intelligence Index v5","description":"Artificial Analysis has published a leaderboard for HLE-Diamond, a refined 1,000-question version of Humanity's Last Exam.","retrieval_nugget":"Artificial Analysis has published a leaderboard for HLE-Diamond, a refined 1,000-question version of Humanity's Last Exam. The page adds independent model runs, split scores, and cost and speed views to a difficult academic benchmark, giving AI builders another comparison signal while leaving real tool-using work unmeasured.","published_at":"2026-10-30","updated_at":"2026-10-30","record_date":"2026-10-30","date_kind":"published_at","topics":["claude","gemini","tool-use"],"entities":["Artificial Analysis","HLE-Diamond","Humanity's Last Exam","Center for AI Safety","Scale AI","Gemini 4 Carbon","Claude Opus 5.5","GPT-5.6 Luna"],"related_patterns":["agent-economics-moves-to-completed-work"],"novelty_label":"new_fact","what_changed":"Artificial Analysis now lists HLE-Diamond as an evaluation in Index v5: a refined 1,000-question Humanity’s Last Exam set, including 272 image questions, run without tools.","prior_refs":["memory:8d70f322-08cd-891e-adcb-97265a979fcb","memory:ea76f0dc-dd9a-8e3e-a4b4-11e3a8ddaef5"],"source_url":"https://artificialanalysis.ai/evaluations/hle-diamond","source_urls":["https://artificialanalysis.ai/evaluations/hle-diamond"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:artificial-analysis-launches-hle-diamond-leaderboard-as-part-0fef9e","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-launches-hle-diamond-leaderboard-as-part-0fef9e/","markdown":"https://newruntime.com/posts/artificial-analysis-launches-hle-diamond-leaderboard-as-part-0fef9e.md","json":"https://newruntime.com/posts/artificial-analysis-launches-hle-diamond-leaderboard-as-part-0fef9e.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":"topic","path":"/topics/tool-use/","url":"https://newruntime.com/topics/tool-use/","title":"Tool Use","reason":"Explore the tool-use topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/tool-use.md","json_url":"https://newruntime.com/topics/tool-use.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"}]}