{"type":"post","id":"new-benchmarks-cognition-s-frontiercode-2-0-merge-a78e19","slug":"new-benchmarks-cognition-s-frontiercode-2-0-merge-a78e19","title":"New benchmarks: Cognition's FrontierCode 2.0 (merge-worthy PRs) and Terminal-Bench-Science (70 agentic science tasks)","description":"Artificial Analysis has released version 5.0 of its Intelligence Index, changing both the evaluations and their weights.","retrieval_nugget":"Artificial Analysis has released version 5.0 of its Intelligence Index, changing both the evaluations and their weights. The index now gives equal weight to knowledge work, coding, science, and general capability, while moving about 60% of its measurement onto private test sets or held-out answers. For AI builders, a familiar leaderboard is becoming less reproducible but potentially harder to game.","published_at":"2026-10-28","updated_at":"2026-10-28","record_date":"2026-10-28","date_kind":"published_at","topics":["knowledge-work"],"entities":["Artificial Analysis","Artificial Analysis Intelligence Index","FrontierCode 2.0","Terminal-Bench-Science 0.1","HLE-Diamond","CritPt v2"],"related_patterns":["verification-bandwidth-is-the-scarce-resource"],"novelty_label":"new_fact","what_changed":"Artificial Analysis now includes FrontierCode 2.0 and Terminal-Bench-Science 0.1 in its benchmarking methodology, describing the latter as 70 agentic science tasks.","prior_refs":["memory:d7d86233-324b-8077-a561-8fe75ffe2ef1","memory:0756f5c8-75d3-81f3-abbf-3293a4f1cb11"],"source_url":"https://artificialanalysis.ai/methodology/intelligence-benchmarking","source_urls":["https://artificialanalysis.ai/methodology/intelligence-benchmarking"],"schema_version":"newruntime-agent-readable-v0.2","stable_id":"post:new-benchmarks-cognition-s-frontiercode-2-0-merge-a78e19","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/new-benchmarks-cognition-s-frontiercode-2-0-merge-a78e19/","markdown":"https://newruntime.com/posts/new-benchmarks-cognition-s-frontiercode-2-0-merge-a78e19.md","json":"https://newruntime.com/posts/new-benchmarks-cognition-s-frontiercode-2-0-merge-a78e19.json"},"next_reads":[{"type":"topic","path":"/topics/knowledge-work/","url":"https://newruntime.com/topics/knowledge-work/","title":"Knowledge Work","reason":"Explore the knowledge-work topic hub.","media_type":"text/html","markdown_url":"https://newruntime.com/topics/knowledge-work.md","json_url":"https://newruntime.com/topics/knowledge-work.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"}]}